chore: import upstream snapshot with attribution
CodeQL / Analyze (csharp) (push) Waiting to run
CodeQL / Analyze (python) (push) Waiting to run
dotnet-build-and-test / dotnet-test-functions (push) Has been cancelled
dotnet-build-and-test / paths-filter (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Debug, windows-latest, net9.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, ubuntu-latest, net8.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-build (Release, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, ubuntu-latest, net10.0) (push) Has been cancelled
dotnet-build-and-test / dotnet-test (Release, integration, true, windows-latest, net472) (push) Has been cancelled
dotnet-build-and-test / dotnet-foundry-hosted-it (push) Has been cancelled
dotnet-build-and-test / dotnet-build-and-test-check (push) Has been cancelled
dotnet-build-and-test / Integration Test Report (push) Has been cancelled

This commit is contained in:
wehub-resource-sync
2026-07-13 13:39:25 +08:00
commit db620d33df
5151 changed files with 925932 additions and 0 deletions
@@ -0,0 +1,34 @@
# Context Provider Samples
These samples demonstrate how to use context providers to enrich agent conversations with external knowledge — from custom logic to Azure AI Search (RAG) and memory services.
## Samples
| File / Folder | Description |
|---------------|-------------|
| [`simple_context_provider.py`](simple_context_provider.py) | Implement a custom context provider by extending `ContextProvider` to extract and inject structured user information across turns. |
| [`azure_ai_foundry_memory.py`](azure_ai_foundry_memory.py) | Use `FoundryMemoryProvider` to add semantic memory — automatically retrieves, searches, and stores memories via Azure AI Foundry. |
| [`file_access_data_processing/`](file_access_data_processing/) | Use `FileAccessProvider` with `FileSystemAgentFileStore` to give an agent read/write/search access to a folder of CSV data files. See its own [README](file_access_data_processing/README.md). |
| [`azure_ai_search/`](azure_ai_search/) | Retrieval Augmented Generation (RAG) with Azure AI Search in semantic and agentic modes. See its own [README](azure_ai_search/README.md). |
| [`mem0/`](mem0/) | Memory-powered context using the Mem0 integration (open-source and managed). See its own [README](mem0/README.md). |
| [`redis/`](redis/) | Redis-backed context providers for conversation memory and sessions. See its own [README](redis/README.md). |
## Prerequisites
**For `simple_context_provider.py`:**
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `FOUNDRY_MODEL`: Model deployment name
- Azure CLI authentication (`az login`)
**For `azure_ai_foundry_memory.py`:**
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `FOUNDRY_MODEL`: Chat/responses model deployment name
- `AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME`: Embedding model deployment name (e.g., `text-embedding-ada-002`)
- Azure CLI authentication (`az login`)
**For `file_access_data_processing/`:**
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `FOUNDRY_MODEL`: Chat model deployment name
- Azure CLI authentication (`az login`)
See each subfolder's README for provider-specific prerequisites.
@@ -0,0 +1,173 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from datetime import datetime, timezone
from agent_framework import Agent, InMemoryHistoryProvider
from agent_framework.foundry import FoundryChatClient, FoundryMemoryProvider
from azure.ai.projects.aio import AIProjectClient
from azure.ai.projects.models import (
MemoryStoreDefaultDefinition,
MemoryStoreDefaultOptions,
)
from azure.identity.aio import AzureCliCredential
from dotenv import load_dotenv
"""
Azure AI Agent with Foundry Memory Context Provider Example
This sample demonstrates using the FoundryMemoryProvider as a context provider
to add semantic memory capabilities to your agents. The provider automatically:
1. Retrieves static (user profile) memories on first run
2. Searches for contextual memories based on conversation
3. Updates the memory store with new conversation messages
The sample creates a temporary memory store with user profile enabled (and chat summary
disabled), scopes memories to a specific user ID ("user_123"), and sets update_delay=0
so memories are stored immediately (in production, use a delay to batch updates and
reduce costs). Conversation history is intentionally not stored (neither service-side
via ``store=False`` nor client-side via ``load_messages=False`` on the history provider),
so that follow-up responses demonstrate the agent relying solely on Foundry Memory
rather than chat history. The memory store is deleted at the end of the run.
Prerequisites:
1. Set FOUNDRY_PROJECT_ENDPOINT environment variable
2. Set FOUNDRY_MODEL for the chat/responses model
3. Set AZURE_OPENAI_EMBEDDING_MODEL for the embedding model
4. Deploy both a chat model (e.g. gpt-4) and an embedding model (e.g. text-embedding-3-small)
"""
load_dotenv()
async def main() -> None:
endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
async with (
AzureCliCredential() as credential,
AIProjectClient(endpoint=endpoint, credential=credential) as project_client,
):
# Generate a unique memory store name to avoid conflicts
memory_store_name = f"agent_framework_memory_{datetime.now(timezone.utc).strftime('%Y%m%d')}"
# Specify memory store options
options = MemoryStoreDefaultOptions(
chat_summary_enabled=False,
user_profile_enabled=True,
user_profile_details="Avoid irrelevant or sensitive data, such as age, financials, precise location, and credentials",
)
memory_store_definition = MemoryStoreDefaultDefinition(
chat_model=os.environ["FOUNDRY_MODEL"],
embedding_model=os.environ["AZURE_OPENAI_EMBEDDING_MODEL"],
options=options,
)
print(f"Creating memory store '{memory_store_name}'...")
try:
# Create a memory store
memory_store = await project_client.beta.memory_stores.create(
name=memory_store_name,
description="Memory store for Agent Framework with FoundryMemoryProvider",
definition=memory_store_definition,
)
except Exception as e:
print(f"Failed to create memory store: {e}")
return
print(f"Created memory store: {memory_store.name} ({memory_store.id})")
print(f"Description: {memory_store.description}\n")
print("==========================================")
# Create the chat client
client = FoundryChatClient(project_client=project_client)
# Create the Foundry Memory context provider
memory_provider = FoundryMemoryProvider(
project_client=project_client,
memory_store_name=memory_store.name,
scope="user_123", # Scope memories to a specific user, if not set, the session_id
# will be used as scope, which means memories are only shared within the same session
update_delay=0, # Do not wait to update memories after each interaction (for demo purposes)
# In production, consider setting a delay to batch updates and reduce costs
)
# Create an agent with the memory context provider
async with Agent(
name="MemoryAgent",
client=client,
instructions="""You are a helpful assistant that remembers past conversations.
The memories from previous interactions are automatically provided to you.""",
context_providers=[memory_provider, InMemoryHistoryProvider(load_messages=False)],
default_options={"store": False},
) as agent:
try:
# note that we will use the service side storage, nor load messsages from the history provider,
# but we include it to demonstrate that it can be used alongside the Foundry provider for other use cases.
session = agent.create_session()
# First interaction - establish some preferences
print("=== First conversation ===")
query1 = "I prefer dark roast coffee and I'm allergic to nuts"
print(f"User: {query1}")
result1 = await agent.run(query1, session=session)
print(f"Agent: {result1}\n")
# Wait for memories to be processed
print("Waiting for memories to be stored...")
await asyncio.sleep(8)
# Second interaction - test memory recall
print("=== Second conversation ===")
query2 = "Can you recommend a coffee and snack for me?"
print(f"User: {query2}")
result2 = await agent.run(query2, session=session)
print(f"Agent: {result2}\n")
# Third interaction - continue the conversation
print("=== Third conversation ===")
query3 = "What do you remember about my preferences?"
print(f"User: {query3}")
result3 = await agent.run(query3, session=session)
print(f"Agent: {result3}\n")
print(f"Stored memories from: {memory_store.name} ({memory_store.id})")
res = await project_client.beta.memory_stores.search_memories(name=memory_store.name, scope="user_123")
for memory in res.memories:
print(f"Memory: {memory.memory_item.content}")
except Exception as e:
print(f"An error occurred: {e}")
finally:
await project_client.beta.memory_stores.delete(memory_store_name)
print("==========================================")
print("Memory store deleted")
if __name__ == "__main__":
asyncio.run(main())
"""
Example output:
Creating memory store 'agent_framework_memory_20260223'...
Created memory store: agent_framework_memory_20260223 (memstore_57c1f95bb4040c6d00RVOP71Q8tS23opIc4G4ZE8DuALiBFx44)
Description: Memory store for Agent Framework with FoundryMemoryProvider
==========================================
=== First conversation ===
User: I prefer dark roast coffee and I'm allergic to nuts
Agent: Got it—Ill remember: you prefer dark roast coffee, and youre allergic to nuts.
Waiting for memories to be stored...
=== Second conversation ===
User: Can you recommend a coffee and snack for me?
Agent: For coffee: **dark roast drip or Americano** (choose a **dark roast** like French/Italian roast). If you like it smoother, try a **dark-roast cold brew**.
For a snack (nut-free): **Greek yogurt with berries**, or a **cheese stick + whole-grain crackers**. If you want something sweet: **dark chocolate (check “may contain nuts” warnings)**.
=== Third conversation ===
User: What do you remember about my preferences?
Agent: - Youre allergic to nuts.
- You prefer dark roast coffee.
Stored memories from: agent_framework_memory_20260223 (memstore_57c1f95bb4040c6d00RVOP71Q8tS23opIc4G4ZE8DuALiBFx44)
Memory: The user is allergic to nuts.
Memory: The user prefers dark roast coffee.
==========================================
Memory store deleted
"""
@@ -0,0 +1,284 @@
# Azure AI Search Context Provider Examples
Azure AI Search context provider enables Retrieval Augmented Generation (RAG) with your agents by retrieving relevant documents from Azure AI Search indexes. It supports two search modes optimized for different use cases.
This folder contains examples demonstrating how to use the Azure AI Search context provider with the Agent Framework.
## Examples
| File | Description |
|------|-------------|
| [`search_context_agentic.py`](search_context_agentic.py) | **Agentic mode** (recommended for most scenarios): Uses Knowledge Bases in Azure AI Search for query planning and multi-hop reasoning. Provides more accurate results through intelligent retrieval with automatic query reformulation. Slightly slower with more token consumption for query planning. [Learn more](https://learn.microsoft.com/azure/search/agentic-retrieval-overview) |
| [`search_context_semantic.py`](search_context_semantic.py) | **Semantic mode** (fast queries): Fast hybrid search combining vector and keyword search with semantic ranking. Returns raw search results as context. Best for scenarios where speed is critical and simple retrieval is sufficient. |
## Installation
```bash
pip install agent-framework-azure-ai-search agent-framework-foundry
```
## Prerequisites
### Required Resources
1. **Azure AI Search service** with a search index containing your documents
- [Create Azure AI Search service](https://learn.microsoft.com/azure/search/search-create-service-portal)
- [Create and populate a search index](https://learn.microsoft.com/azure/search/search-what-is-an-index)
2. **Azure AI Foundry project** with a model deployment
- [Create Azure AI Foundry project](https://learn.microsoft.com/azure/ai-studio/how-to/create-projects)
- Deploy a model (e.g., GPT-4o)
3. **For Agentic mode only**: Azure OpenAI resource for Knowledge Base model calls
- [Create Azure OpenAI resource](https://learn.microsoft.com/azure/ai-services/openai/how-to/create-resource)
- Note: This is separate from your Azure AI Foundry project endpoint
### Authentication
Both examples support two authentication methods:
- **API Key**: Set `AZURE_SEARCH_API_KEY` environment variable
- **Entra ID (Managed Identity)**: Uses `DefaultAzureCredential` when API key is not provided
Run `az login` if using Entra ID authentication.
### API versions (stable vs preview)
The provider auto-detects which build of `azure-search-documents` is installed — nothing to
configure in code:
- **Stable / GA** — `pip install azure-search-documents` (`>=12.0.0`) → api-version `2026-04-01`.
- **Preview** — `pip install --pre azure-search-documents` (e.g. `12.1.0b1`) → api-version `2026-05-01-preview`.
The installed build picks its own api-version, so newer releases work without code changes.
Agentic `knowledge_base_output_mode="answer_synthesis"` and `retrieval_reasoning_effort` of
`"low"`/`"medium"` ship **only** in the preview build. On a stable build the provider uses
extractive output with minimal reasoning effort and raises an actionable error if a preview-only
option is requested. To enable them, just install the preview build (`pip install --pre
azure-search-documents`) — no code change.
## Configuration
### Environment Variables
**Common (both modes):**
- `AZURE_SEARCH_ENDPOINT`: Your Azure AI Search endpoint (e.g., `https://myservice.search.windows.net`)
- `AZURE_SEARCH_INDEX_NAME`: Name of your search index
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `FOUNDRY_MODEL`: Model deployment name (e.g., `gpt-4o`, defaults to `gpt-4o`)
- `AZURE_SEARCH_API_KEY`: _(Optional)_ Your search API key - if not provided, uses DefaultAzureCredential
**Agentic mode only:**
- `AZURE_SEARCH_KNOWLEDGE_BASE_NAME`: Name of your Knowledge Base in Azure AI Search
- `AZURE_OPENAI_RESOURCE_URL`: Your Azure OpenAI resource URL (e.g., `https://myresource.openai.azure.com`)
- **Important**: This is different from `FOUNDRY_PROJECT_ENDPOINT` - Knowledge Base needs the OpenAI endpoint for model calls
### Example .env file
**For Semantic Mode:**
```env
AZURE_SEARCH_ENDPOINT=https://myservice.search.windows.net
AZURE_SEARCH_INDEX_NAME=my-index
FOUNDRY_PROJECT_ENDPOINT=https://<resource-name>.services.ai.azure.com/api/projects/<project-name>
FOUNDRY_MODEL=gpt-4o
# Optional - omit to use Entra ID
AZURE_SEARCH_API_KEY=your-search-key
```
**For Agentic Mode (add these to semantic mode variables):**
```env
AZURE_SEARCH_KNOWLEDGE_BASE_NAME=my-knowledge-base
AZURE_OPENAI_RESOURCE_URL=https://myresource.openai.azure.com
```
## Search Modes Comparison
| Feature | Semantic Mode | Agentic Mode |
|---------|--------------|--------------|
| **Speed** | Fast | Slower (query planning overhead) |
| **Token Usage** | Lower | Higher (query reformulation) |
| **Retrieval Strategy** | Hybrid search + semantic ranking | Multi-hop reasoning with Knowledge Base |
| **Query Handling** | Direct search | Automatic query reformulation |
| **Best For** | Simple queries, speed-critical apps | Complex queries, multi-document reasoning |
| **Additional Setup** | None | Requires Knowledge Base + OpenAI resource |
### When to Use Semantic Mode
- **Simple queries** where direct keyword/vector search is sufficient
- **Speed is critical** and you need low latency
- **Straightforward retrieval** from single documents
- **Lower token costs** are important
### When to Use Agentic Mode
- **Complex queries** requiring multi-hop reasoning
- **Cross-document analysis** where information spans multiple sources
- **Ambiguous queries** that benefit from automatic reformulation
- **Higher accuracy** is more important than speed
- You need **intelligent query planning** and document synthesis
## How the Examples Work
### Semantic Mode Flow
1. User query is sent to Azure AI Search
2. Hybrid search (vector + keyword) retrieves relevant documents
3. Semantic ranking reorders results for relevance
4. Top-k documents are returned as context
5. Agent generates response using retrieved context
### Agentic Mode Flow
1. User query is sent to the Knowledge Base
2. Knowledge Base plans the retrieval strategy
3. Multiple search queries may be executed (multi-hop)
4. Retrieved information is synthesized
5. Enhanced context is provided to the agent
6. Agent generates response with comprehensive context
## Code Example
### Semantic Mode
```python
from agent_framework import Agent
from agent_framework.azure import AzureAISearchContextProvider
from agent_framework.foundry import FoundryChatClient
from azure.identity.aio import DefaultAzureCredential
# Create search provider with semantic mode (default)
search_provider = AzureAISearchContextProvider(
endpoint=search_endpoint,
index_name=index_name,
api_key=search_key, # Or use credential for Entra ID
mode="semantic", # Default mode
top_k=3, # Number of documents to retrieve
)
# Create agent with search context
async with FoundryChatClient(
project_endpoint=project_endpoint,
model=model_deployment,
credential=DefaultAzureCredential(),
) as client:
async with Agent(
client=client,
context_providers=[search_provider],
) as agent:
response = await agent.run("What information is in the knowledge base?")
```
### Agentic Mode
```python
from agent_framework.azure import AzureAISearchContextProvider
# Create search provider with agentic mode
search_provider = AzureAISearchContextProvider(
endpoint=search_endpoint,
index_name=index_name,
api_key=search_key,
mode="agentic", # Enable agentic retrieval
knowledge_base_name=knowledge_base_name,
azure_openai_resource_url=azure_openai_resource_url,
top_k=5,
)
# Use with agent (same as semantic mode)
async with Agent(
client=client,
model=model_deployment,
context_providers=[search_provider],
) as agent:
response = await agent.run("Analyze and compare topics across documents")
```
## Running the Examples
1. **Set up environment variables** (see Configuration section above)
2. **Ensure you have an Azure AI Search index** with documents:
```bash
# Verify your index exists
curl -X GET "https://myservice.search.windows.net/indexes/my-index?api-version=2024-07-01" \
-H "api-key: YOUR_API_KEY"
```
3. **For agentic mode**: Create a Knowledge Base in Azure AI Search
- [Knowledge Base documentation](https://learn.microsoft.com/azure/search/knowledge-store-create-portal)
4. **Run the examples**:
```bash
# Semantic mode (fast, simple)
python azure_ai_with_search_context_semantic.py
# Agentic mode (intelligent, complex)
python azure_ai_with_search_context_agentic.py
```
## Key Parameters
### Common Parameters
- `endpoint`: Azure AI Search service endpoint
- `index_name`: Name of the search index
- `api_key`: API key for authentication (optional, can use credential instead)
- `credential`: Azure credential for Entra ID auth (e.g., `DefaultAzureCredential()`)
- `mode`: Search mode - `"semantic"` (default) or `"agentic"`
- `top_k`: Number of documents to retrieve (default: 3 for semantic, 5 for agentic)
### Semantic Mode Parameters
- `semantic_configuration`: Name of semantic configuration in your index (optional)
- `query_type`: Query type - `"semantic"` for semantic search (default)
### Agentic Mode Parameters
- `knowledge_base_name`: Name of your Knowledge Base (required)
- `azure_openai_resource_url`: Azure OpenAI resource URL (required)
- `max_search_queries`: Maximum number of search queries to generate (default: 3)
## Troubleshooting
### Common Issues
1. **Authentication errors**
- Ensure `AZURE_SEARCH_API_KEY` is set, or run `az login` for Entra ID auth
- Verify your credentials have search permissions
2. **Index not found**
- Verify `AZURE_SEARCH_INDEX_NAME` matches your index name exactly
- Check that the index exists and contains documents
3. **Agentic mode errors**
- Ensure `AZURE_SEARCH_KNOWLEDGE_BASE_NAME` is correctly configured
- Verify `AZURE_OPENAI_RESOURCE_URL` points to your Azure OpenAI resource (not AI Foundry endpoint)
- Check that your OpenAI resource has the necessary model deployments
4. **No results returned**
- Verify your index has documents with vector embeddings (for semantic/hybrid search)
- Check that your queries match the content in your index
- Try increasing `top_k` parameter
5. **Slow responses in agentic mode**
- This is expected - agentic mode trades speed for accuracy
- Reduce `max_search_queries` if needed
- Consider semantic mode for speed-critical applications
## Performance Tips
- **Use semantic mode** as the default for most scenarios - it's fast and effective
- **Switch to agentic mode** when you need multi-hop reasoning or complex queries
- **Adjust `top_k`** based on your needs - higher values provide more context but increase token usage
- **Enable semantic configuration** in your index for better semantic ranking
- **Use Entra ID authentication** in production for better security
## Additional Resources
- [Azure AI Search Documentation](https://learn.microsoft.com/azure/search/)
- [Azure AI Foundry Documentation](https://learn.microsoft.com/azure/ai-studio/)
- [RAG with Azure AI Search](https://learn.microsoft.com/azure/search/retrieval-augmented-generation-overview)
- [Semantic Search in Azure AI Search](https://learn.microsoft.com/azure/search/semantic-search-overview)
- [Knowledge Bases in Azure AI Search](https://learn.microsoft.com/azure/search/knowledge-store-concept-intro)
- [Agentic Retrieval in Azure AI Search](https://learn.microsoft.com/azure/search/agentic-retrieval-overview)
@@ -0,0 +1,150 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from agent_framework import Agent
from agent_framework.azure import AzureAISearchContextProvider
from agent_framework.foundry import FoundryChatClient
from azure.identity.aio import AzureCliCredential
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
"""
This sample demonstrates how to use Azure AI Search with agentic mode for RAG
(Retrieval Augmented Generation) with Azure AI agents.
**Agentic mode** is recommended for most scenarios:
- Uses Knowledge Bases in Azure AI Search for query planning
- Performs multi-hop reasoning across documents
- Provides more accurate results through intelligent retrieval
- Slightly slower with more token consumption for query planning
- See: https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/foundry-iq-boost-response-relevance-by-36-with-agentic-retrieval/4470720
For simple queries where speed is critical, use semantic mode instead (see azure_ai_with_search_context_semantic.py).
Prerequisites:
1. An Azure AI Search service
2. An Azure AI Foundry project with a model deployment
3. Either an existing Knowledge Base OR a search index (to auto-create a KB)
Environment variables:
- AZURE_SEARCH_ENDPOINT: Your Azure AI Search endpoint
- AZURE_SEARCH_API_KEY: (Optional) API key - if not provided, uses AzureCliCredential
- FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
- FOUNDRY_MODEL: Your model deployment name (e.g., "gpt-4o")
For using an existing Knowledge Base (recommended):
- AZURE_SEARCH_KNOWLEDGE_BASE_NAME: Your Knowledge Base name
For auto-creating a Knowledge Base from an index:
- AZURE_SEARCH_INDEX_NAME: Your search index name
- AZURE_OPENAI_RESOURCE_URL: Azure OpenAI resource URL (e.g., "https://myresource.openai.azure.com")
"""
# Sample queries to demonstrate agentic RAG
USER_INPUTS = [
"What information is available in the knowledge base?",
"Analyze and compare the main topics from different documents",
"What connections can you find across different sections?",
]
async def main() -> None:
"""Main function demonstrating Azure AI Search agentic mode."""
# Get configuration from environment
search_endpoint = os.environ["AZURE_SEARCH_ENDPOINT"]
search_key = os.environ.get("AZURE_SEARCH_API_KEY")
project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
model_deployment = os.environ.get("FOUNDRY_MODEL", "gpt-4o")
# Agentic mode requires exactly ONE of: knowledge_base_name OR index_name
# Option 1: Use existing Knowledge Base (recommended)
knowledge_base_name = os.environ.get("AZURE_SEARCH_KNOWLEDGE_BASE_NAME")
# Option 2: Auto-create KB from index (requires azure_openai_resource_url)
index_name = os.environ.get("AZURE_SEARCH_INDEX_NAME")
azure_openai_resource_url = os.environ.get("AZURE_OPENAI_RESOURCE_URL")
# Create Azure AI Search context provider with agentic mode (recommended for accuracy)
print("Using AGENTIC mode (Knowledge Bases with query planning, recommended)\n")
print("This mode is slightly slower but provides more accurate results.\n")
# Configure based on whether using existing KB or auto-creating from index
if knowledge_base_name:
# Use existing Knowledge Base - simplest approach
search_provider = AzureAISearchContextProvider(
source_id="search_provider",
endpoint=search_endpoint,
api_key=search_key,
credential=AzureCliCredential() if not search_key else None,
mode="agentic",
knowledge_base_name=knowledge_base_name,
# Optional: Configure retrieval behavior. "answer_synthesis" output mode and
# "medium"/"low" reasoning effort require the preview build of azure-search-documents
# (`pip install --pre azure-search-documents`); the provider auto-detects the build.
knowledge_base_output_mode="extractive_data", # or "answer_synthesis" (preview build only)
retrieval_reasoning_effort="minimal", # or "medium", "low" (preview build only)
)
else:
# Auto-create Knowledge Base from index
if not index_name:
raise ValueError("Set AZURE_SEARCH_KNOWLEDGE_BASE_NAME or AZURE_SEARCH_INDEX_NAME")
if not azure_openai_resource_url:
raise ValueError("AZURE_OPENAI_RESOURCE_URL required when using index_name")
search_provider = AzureAISearchContextProvider(
source_id="search_provider",
endpoint=search_endpoint,
index_name=index_name,
api_key=search_key,
credential=AzureCliCredential() if not search_key else None,
mode="agentic",
azure_openai_resource_url=azure_openai_resource_url,
model=model_deployment,
# Optional: Configure retrieval behavior. "answer_synthesis" output mode and
# "medium"/"low" reasoning effort require the preview build of azure-search-documents
# (`pip install --pre azure-search-documents`); the provider auto-detects the build.
knowledge_base_output_mode="extractive_data", # or "answer_synthesis" (preview build only)
retrieval_reasoning_effort="minimal", # or "medium", "low" (preview build only)
top_k=3,
)
# Create agent with search context provider
async with (
search_provider,
Agent(
client=FoundryChatClient(
project_endpoint=project_endpoint,
model=model_deployment,
credential=AzureCliCredential(),
),
name="SearchAgent",
instructions=(
"You are a helpful assistant with advanced reasoning capabilities. "
"Use the provided context from the knowledge base to answer complex "
"questions that may require synthesizing information from multiple sources."
),
context_providers=[search_provider],
) as agent,
):
print("=== Azure AI Agent with Search Context (Agentic Mode) ===\n")
for user_input in USER_INPUTS:
print(f"User: {user_input}")
print("Agent: ", end="", flush=True)
# Stream response
async for chunk in agent.run(user_input, stream=True):
if chunk.text:
print(chunk.text, end="", flush=True)
for content in chunk.contents:
if content.annotations:
print(f"\n[Sources: {content.annotations}]", end="", flush=True)
print("\n")
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,117 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from agent_framework import Agent
from agent_framework.azure import AzureAISearchContextProvider
from agent_framework.foundry import FoundryChatClient
from agent_framework.openai import OpenAIEmbeddingClient
from azure.identity.aio import AzureCliCredential
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
"""
This sample demonstrates how to use Azure AI Search with semantic mode for RAG
(Retrieval Augmented Generation) with Azure AI agents.
**Semantic mode** is the recommended default mode:
- Fast hybrid search combining vector and keyword search
- Uses semantic ranking for improved relevance
- Returns raw search results as context
- Best for most RAG use cases
Prerequisites:
1. An Azure AI Search service with a search index
2. An Azure AI Foundry project with a model deployment
3. Set the following environment variables:
- AZURE_SEARCH_ENDPOINT: Your Azure AI Search endpoint
- AZURE_SEARCH_API_KEY: (Optional) Your search API key - if not provided, uses AzureCliCredential for Entra ID
- AZURE_SEARCH_INDEX_NAME: Your search index name
- FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
- FOUNDRY_MODEL: Your model deployment name (e.g., "gpt-4o")
- AZURE_OPENAI_EMBEDDING_MODEL: (Optional) Your Azure OpenAI embedding deployment for hybrid search
- AZURE_OPENAI_ENDPOINT: (Optional) Your Azure OpenAI resource URL, required if using Azure OpenAI embeddings
"""
# Sample queries to demonstrate RAG
USER_INPUTS = [
"What information is available in the knowledge base?",
"Summarize the main topics from the documents",
"Find specific details about the content",
]
async def main() -> None:
"""Main function demonstrating Azure AI Search semantic mode."""
credential = AzureCliCredential()
# Get configuration from environment
search_endpoint = os.environ["AZURE_SEARCH_ENDPOINT"]
search_key = os.environ.get("AZURE_SEARCH_API_KEY")
index_name = os.environ["AZURE_SEARCH_INDEX_NAME"]
project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
model_deployment = os.environ.get("FOUNDRY_MODEL", "gpt-4o")
openai_endpoint = os.environ.get("AZURE_OPENAI_ENDPOINT")
embedding_deployment = os.environ.get("AZURE_OPENAI_EMBEDDING_MODEL")
embedding_client = None
if openai_endpoint and embedding_deployment:
embedding_client = OpenAIEmbeddingClient(
azure_endpoint=openai_endpoint,
model=embedding_deployment,
credential=credential,
)
# Create Azure AI Search context provider with semantic mode (recommended, fast)
print("Using SEMANTIC mode (hybrid search + semantic ranking, fast)\n")
search_provider = AzureAISearchContextProvider(
source_id="search_provider",
endpoint=search_endpoint,
index_name=index_name,
api_key=search_key, # Use api_key for API key auth, or credential for managed identity
credential=credential if not search_key else None,
mode="semantic", # Default mode
top_k=3, # Retrieve top 3 most relevant documents
embedding_function=embedding_client, # Provide embedding function for hybrid search
vector_field_name="DescriptionVector"
if embedding_client
else None, # Set vector field for hybrid search if using embeddings
)
# Create agent with search context provider
async with (
search_provider,
Agent(
client=FoundryChatClient(
project_endpoint=project_endpoint,
model=model_deployment,
credential=credential,
),
name="SearchAgent",
instructions=(
"You are a helpful assistant. Use the provided context from the "
"knowledge base to answer questions accurately."
),
context_providers=[search_provider],
) as agent,
):
print("=== Azure AI Agent with Search Context (Semantic Mode) ===\n")
for user_input in USER_INPUTS:
print(f"User: {user_input}")
print("Agent: ", end="", flush=True)
# Stream response
async for chunk in agent.run(user_input, stream=True):
if chunk.text:
print(chunk.text, end="", flush=True)
print("\n")
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,43 @@
# CodeAct context providers
Demonstrates the provider-owned CodeAct flow with two backends:
| File | Backend | Notes |
|------|---------|-------|
| [`code_act.py`](code_act.py) | [Hyperlight](https://github.com/hyperlight-dev/hyperlight) WASM sandbox via `HyperlightCodeActProvider` | Hardened sandbox with WASM isolation; sandbox tools called via `call_tool(...)`. |
| [`monty_code_act.py`](monty_code_act.py) | [Monty](https://github.com/pydantic/monty) Rust-based Python interpreter via `MontyCodeActProvider` (alpha) | Cross-platform pure interpreter; sandbox tools can be called as typed async functions (`await compute(...)`) or via `call_tool(...)`. |
Both providers inject an `execute_code` tool into the agent and keep the
registered sandbox tools (`compute`, `fetch_data`) hidden from the model — the
model invokes them from inside the sandbox.
## Installation
```bash
pip install agent-framework agent-framework-hyperlight --pre # Hyperlight sample
pip install agent-framework agent-framework-monty --pre # Monty sample
```
> The Hyperlight Wasm backend is currently published only for `linux/x86_64` and
> `win32/AMD64` with Python `<3.14`. On other platforms `execute_code` will fail
> at runtime when it tries to create the sandbox.
>
> Monty is cross-platform and has no hypervisor/WASM backend dependency, but it
> interprets a Python subset (e.g. `os`/network/subprocess access is blocked).
> `agent-framework-monty` is an alpha package and is not yet part of
> `agent-framework[all]`; install it explicitly with `--pre`.
## Prerequisites
- An Azure AI Foundry project endpoint (`FOUNDRY_PROJECT_ENDPOINT`)
- A deployed model (`FOUNDRY_MODEL`)
- Azure CLI authenticated (`az login`)
## Run
```bash
python code_act.py # Hyperlight
python monty_code_act.py # Monty
```
See the source files for the full annotated examples.
@@ -0,0 +1,187 @@
# Copyright (c) Microsoft. All rights reserved.
from __future__ import annotations
import asyncio
import logging
import os
from collections.abc import Awaitable, Callable
from typing import Annotated, Any, Literal
from agent_framework import Agent, FunctionInvocationContext, function_middleware, tool
from agent_framework.foundry import FoundryChatClient
from agent_framework.hyperlight import HyperlightCodeActProvider
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
"""This sample demonstrates the provider-owned Hyperlight CodeAct flow.
The sample keeps `compute` and `fetch_data` off the direct agent tool surface and
registers them only with `HyperlightCodeActProvider`. The model therefore sees a
single `execute_code` tool and must call the provider-owned tools from inside
the sandbox with `call_tool(...)`.
"""
load_dotenv()
_CYAN = "\033[36m"
_YELLOW = "\033[33m"
_GREEN = "\033[32m"
_DIM = "\033[2m"
_RESET = "\033[0m"
class _ColoredFormatter(logging.Formatter):
"""Dim logger output so it does not compete with sample prints."""
def format(self, record: logging.LogRecord) -> str:
return f"{_DIM}{super().format(record)}{_RESET}"
logging.basicConfig(level=logging.WARNING)
logging.getLogger().handlers[0].setFormatter(
_ColoredFormatter("[%(asctime)s] %(levelname)s: %(message)s"),
)
@function_middleware
async def log_function_calls(
context: FunctionInvocationContext,
call_next: Callable[[], Awaitable[None]],
) -> None:
"""Log tool calls, including readable execute_code blocks."""
import time
function_name = context.function.name
arguments = context.arguments if isinstance(context.arguments, dict) else {}
if function_name == "execute_code" and "code" in arguments:
print(f"\n{_YELLOW}{'' * 60}")
print("▶ execute_code")
print(f"{'' * 60}{_RESET}")
print(arguments["code"])
print(f"{_YELLOW}{'' * 60}{_RESET}")
else:
pairs = ", ".join(f"{name}={value!r}" for name, value in arguments.items())
print(f"\n{_YELLOW}{function_name}({pairs}){_RESET}")
start = time.perf_counter()
await call_next()
elapsed = time.perf_counter() - start
result = context.result
if function_name == "execute_code" and isinstance(result, list):
for output in result:
if output.type == "text" and output.text:
print(f"{_GREEN}stdout:\n{output.text}{_RESET}")
elif output.type == "error" and output.error_details:
print(f"{_YELLOW}stderr:\n{output.error_details}{_RESET}")
else:
print(f"{_YELLOW}{function_name}{result!r}{_RESET}")
print(f"{_DIM} ({elapsed:.4f}s){_RESET}")
@tool(approval_mode="never_require")
def compute(
operation: Annotated[
Literal["add", "subtract", "multiply", "divide"],
"Math operation: add, subtract, multiply, or divide.",
],
a: Annotated[float, "First numeric operand."],
b: Annotated[float, "Second numeric operand."],
) -> float:
"""Perform a math operation for sandboxed code."""
operations = {
"add": a + b,
"subtract": a - b,
"multiply": a * b,
"divide": a / b if b else float("inf"),
}
return operations[operation]
@tool(approval_mode="never_require")
async def fetch_data(
table: Annotated[str, "Name of the simulated table to query."],
) -> list[dict[str, Any]]:
"""Fetch records from a named table."""
await asyncio.sleep(0.5)
data: dict[str, list[dict[str, Any]]] = {
"users": [
{"id": 1, "name": "Alice", "role": "admin"},
{"id": 2, "name": "Bob", "role": "user"},
{"id": 3, "name": "Charlie", "role": "admin"},
],
"products": [
{"id": 101, "name": "Widget", "price": 9.99},
{"id": 102, "name": "Gadget", "price": 19.99},
],
}
return data.get(table, [])
async def main() -> None:
"""Run the provider-owned Hyperlight CodeAct sample."""
# 1. Create the Hyperlight-backed provider and register sandbox tools on it.
codeact = HyperlightCodeActProvider(
tools=[compute, fetch_data],
approval_mode="never_require",
)
# 2. Create the client and the agent.
agent = Agent(
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
name="HyperlightCodeActProviderAgent",
instructions="You are a helpful assistant.",
context_providers=[codeact],
middleware=[log_function_calls],
)
# 3. Run a request that should use execute_code plus provider-owned tools.
query = (
"Fetch all users, find admins, multiply 7*(3*2), and print the users, "
"admins, and multiplication result. Use execute_code and call_tool(...) "
"inside the sandbox."
)
print(f"{_CYAN}{'=' * 60}")
print("Hyperlight CodeAct provider sample")
print(f"{'=' * 60}{_RESET}")
print(f"{_CYAN}User: {query}{_RESET}")
result = await agent.run(query)
print(f"{_CYAN}Agent: {result.text}{_RESET}")
"""
Sample output (shape only):
============================================================
Hyperlight CodeAct provider sample
============================================================
User: Fetch all users, find admins, multiply 7*(3*2), ...
────────────────────────────────────────────────────────────
▶ execute_code
────────────────────────────────────────────────────────────
users = call_tool("fetch_data", table="users")
admins = [user for user in users if user["role"] == "admin"]
result = call_tool("compute", operation="multiply", a=7, b=6)
print("Users:", users)
print("Admins:", admins)
print("7 * 6 =", result)
────────────────────────────────────────────────────────────
stdout:
Users: [...]
Admins: [...]
7 * 6 = 42.0
(0.0xxx s)
Agent: ...
"""
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,201 @@
# Copyright (c) Microsoft. All rights reserved.
from __future__ import annotations
import asyncio
import logging
import os
from collections.abc import Awaitable, Callable
from typing import Annotated, Any, Literal
from agent_framework import Agent, FunctionInvocationContext, function_middleware, tool
from agent_framework.foundry import FoundryChatClient
from agent_framework_monty import MontyCodeActProvider
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
"""This sample demonstrates the provider-owned Monty CodeAct flow.
The sample keeps `compute` and `fetch_data` off the direct agent tool surface and
registers them only with `MontyCodeActProvider`. The model therefore sees a
single `execute_code` tool and calls the provider-owned tools from inside the
sandbox - either as typed async functions (`await compute(...)`) or via the
generic `call_tool(...)` fallback.
`MontyCodeActProvider` uses [pydantic-monty](https://github.com/pydantic/monty),
a Rust-based Python interpreter, so it runs cross-platform with no
hypervisor/WASM backend dependency.
Note: `agent-framework-monty` is an alpha package and is not yet part of
`agent-framework[all]`. Install it explicitly with:
pip install agent-framework agent-framework-monty --pre
It is imported as `agent_framework_monty` (no lazy-loading namespace yet).
"""
load_dotenv()
_CYAN = "\033[36m"
_YELLOW = "\033[33m"
_GREEN = "\033[32m"
_DIM = "\033[2m"
_RESET = "\033[0m"
class _ColoredFormatter(logging.Formatter):
"""Dim logger output so it does not compete with sample prints."""
def format(self, record: logging.LogRecord) -> str:
return f"{_DIM}{super().format(record)}{_RESET}"
logging.basicConfig(level=logging.WARNING)
logging.getLogger().handlers[0].setFormatter(
_ColoredFormatter("[%(asctime)s] %(levelname)s: %(message)s"),
)
@function_middleware
async def log_function_calls(
context: FunctionInvocationContext,
call_next: Callable[[], Awaitable[None]],
) -> None:
"""Log tool calls, including readable execute_code blocks."""
import time
function_name = context.function.name
arguments = context.arguments if isinstance(context.arguments, dict) else {}
if function_name == "execute_code" and "code" in arguments:
print(f"\n{_YELLOW}{'' * 60}")
print("▶ execute_code")
print(f"{'' * 60}{_RESET}")
print(arguments["code"])
print(f"{_YELLOW}{'' * 60}{_RESET}")
else:
pairs = ", ".join(f"{name}={value!r}" for name, value in arguments.items())
print(f"\n{_YELLOW}{function_name}({pairs}){_RESET}")
start = time.perf_counter()
await call_next()
elapsed = time.perf_counter() - start
result = context.result
if function_name == "execute_code" and isinstance(result, list):
for output in result:
if output.type == "text" and output.text:
print(f"{_GREEN}stdout:\n{output.text}{_RESET}")
elif output.type == "error" and output.error_details:
print(f"{_YELLOW}stderr:\n{output.error_details}{_RESET}")
else:
print(f"{_YELLOW}{function_name}{result!r}{_RESET}")
print(f"{_DIM} ({elapsed:.4f}s){_RESET}")
@tool(approval_mode="never_require")
def compute(
operation: Annotated[
Literal["add", "subtract", "multiply", "divide"],
"Math operation: add, subtract, multiply, or divide.",
],
a: Annotated[float, "First numeric operand."],
b: Annotated[float, "Second numeric operand."],
) -> float:
"""Perform a math operation for sandboxed code."""
operations = {
"add": a + b,
"subtract": a - b,
"multiply": a * b,
"divide": a / b if b else float("inf"),
}
return operations[operation]
@tool(approval_mode="never_require")
async def fetch_data(
table: Annotated[str, "Name of the simulated table to query."],
) -> list[dict[str, Any]]:
"""Fetch records from a named table."""
await asyncio.sleep(0.5)
data: dict[str, list[dict[str, Any]]] = {
"users": [
{"id": 1, "name": "Alice", "role": "admin"},
{"id": 2, "name": "Bob", "role": "user"},
{"id": 3, "name": "Charlie", "role": "admin"},
],
"products": [
{"id": 101, "name": "Widget", "price": 9.99},
{"id": 102, "name": "Gadget", "price": 19.99},
],
}
return data.get(table, [])
async def main() -> None:
"""Run the provider-owned Monty CodeAct sample."""
# 1. Create the Monty-backed provider and register sandbox tools on it.
codeact = MontyCodeActProvider(
tools=[compute, fetch_data],
approval_mode="never_require",
)
# 2. Create the client and the agent.
agent = Agent(
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
name="MontyCodeActProviderAgent",
instructions="You are a helpful assistant.",
context_providers=[codeact],
middleware=[log_function_calls],
)
# 3. Run a request that should use execute_code plus provider-owned tools.
query = (
"Fetch all users, find admins, multiply 7*(3*2), and print the users, "
"admins, and multiplication result. Use a single execute_code call. "
"You may call the registered tools directly as typed async functions "
"(`await compute(operation='multiply', a=7, b=6)`) or via "
"`call_tool('compute', ...)`."
)
print(f"{_CYAN}{'=' * 60}")
print("Monty CodeAct provider sample")
print(f"{'=' * 60}{_RESET}")
print(f"{_CYAN}User: {query}{_RESET}")
result = await agent.run(query)
print(f"{_CYAN}Agent: {result.text}{_RESET}")
"""
Sample output (shape only):
============================================================
Monty CodeAct provider sample
============================================================
User: Fetch all users, find admins, multiply 7*(3*2), ...
────────────────────────────────────────────────────────────
▶ execute_code
────────────────────────────────────────────────────────────
users = await fetch_data(table="users")
admins = [u for u in users if u["role"] == "admin"]
result = await compute(operation="multiply", a=7, b=6)
print("Users:", users)
print("Admins:", admins)
print("7 * 6 =", result)
────────────────────────────────────────────────────────────
stdout:
Users: [...]
Admins: [...]
7 * 6 = 42.0
(0.5xxx s)
Agent: ...
"""
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,62 @@
# File Access Data Processing
This sample demonstrates how to give an `Agent` access to a folder of data files
by attaching `FileAccessProvider` (backed by `FileSystemAgentFileStore`) as a
context provider.
The agent is given a `working/` folder containing `sales.csv` — ~50 rows of
sales transaction data — and is driven through a short scripted conversation
that exercises every tool the provider exposes:
| Step | Prompt | Tool(s) used |
|---|---|---|
| 1 | "What files do you have access to?" | `file_access_ls` |
| 2 | "Read sales.csv and summarize…" | `file_access_read` |
| 3 | "Calculate the total revenue per region…" | (uses previously read data) |
| 4 | "Save a markdown report named `region_totals.md`…" | `file_access_write` |
| 5 | "List the files again so I can confirm…" | `file_access_ls` |
After the run, the sample prints the final contents of `working/` so the
written file is easy to spot.
## Prerequisites
| Variable | Description |
|---|---|
| `FOUNDRY_PROJECT_ENDPOINT` | Your Azure AI Foundry project endpoint. |
| `FOUNDRY_MODEL` | Chat model deployment name (e.g. `gpt-4o`). |
Run `az login` before executing the sample so `AzureCliCredential` can
authenticate.
## Running the sample
From `python/`:
```bash
uv run --package agent-framework-core python samples/02-agents/context_providers/file_access_data_processing/data_processing.py
```
Or directly:
```bash
python samples/02-agents/context_providers/file_access_data_processing/data_processing.py
```
## Sample data
`working/sales.csv` contains JanuaryMarch 2025 sales transactions with these
columns:
| Column | Description |
|---|---|
| `date` | Transaction date (YYYY-MM-DD) |
| `product` | Product name |
| `category` | Product category (Electronics, Furniture, Stationery) |
| `quantity` | Units sold |
| `unit_price` | Price per unit |
| `region` | Sales region (North, South, West) |
| `salesperson` | Name of the salesperson |
The sample writes `region_totals.md` into the same folder. Delete it between
runs if you want a clean state.
@@ -0,0 +1,159 @@
# Copyright (c) Microsoft. All rights reserved.
"""Sample: use ``FileAccessProvider`` to give an agent access to a folder of CSV data files.
This sample demonstrates how to attach :class:`FileAccessProvider` (backed by
:class:`FileSystemAgentFileStore`) to an ``Agent`` so the model can read input
data, perform analysis, and write summary output back to the same folder via
the ``file_access_*`` tools.
The file-access tools all require approval (``approval_mode="always_require"``),
so a base ``Agent`` installs :class:`ToolApprovalMiddleware` to drive the
approval handshake. Because this sample is non-interactive, it auto-approves
every file-access tool via
:meth:`FileAccessProvider.all_tools_auto_approval_rule`.
The sibling ``working/`` folder contains ``sales.csv`` — ~50 rows of sales
transactions (date, product, category, quantity, unit_price, region,
salesperson). The agent is asked, in a single session, to: list available
files, inspect the data, compute regional totals, and save a markdown summary.
Prerequisites:
- ``FOUNDRY_PROJECT_ENDPOINT``: Your Azure AI Foundry project endpoint.
- ``FOUNDRY_MODEL``: Chat model deployment name.
- Run ``az login`` before executing the sample.
"""
import asyncio
import os
from pathlib import Path
from agent_framework import Agent, FileAccessProvider, FileSystemAgentFileStore, ToolApprovalMiddleware
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
# Load python/.env (python-dotenv walks up from this file by default). Pass
# override=True so values from .env take precedence over any pre-existing OS
# environment variables — without this, OS-level values silently win.
load_dotenv(override=True)
INSTRUCTIONS = """
You are a data analyst assistant. You have access to a folder of data files via
the file_access_* tools.
## Getting started
- Start by listing available files with file_access_ls to see what data
is available. Files may be organized into subdirectories — use
file_access_ls to discover folders and explore the tree level
by level.
- Read the files to understand their structure and contents.
## Working with data
- When asked to analyze data, read the relevant files first, then perform the
analysis.
- Show your analysis clearly with tables, summaries, and key insights.
- When calculations are needed, work through them step by step and show your
reasoning.
## Writing output
- When asked to produce output files (e.g., reports, summaries, filtered data),
use file_access_write to write them.
- Use appropriate file formats: CSV for tabular data, Markdown for reports.
- Confirm what you wrote and where.
## Important
- Never modify or delete the original input data files unless explicitly asked
to do so.
- If asked about data you haven't read yet, read it first before answering.
- Always explain your reasoning between tool calls so the user can follow along.
"""
PROMPTS = [
"What files do you have access to?",
"Read sales.csv and summarize what columns it contains and how many rows it has.",
"Calculate the total revenue (quantity * unit_price) per region and show the result as a table.",
(
"Save a markdown report named region_totals.md that contains the regional totals "
"and a one-paragraph summary of which region performed best."
),
"List the files again so I can confirm region_totals.md was created.",
]
async def main() -> None:
# 1. Resolve the working directory bundled alongside this script.
working_dir = Path(__file__).parent / "working"
# 2. Build the chat client.
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
# 3. Wire up the file access provider against a file-system-backed store
# rooted at the sample's working/ folder. The provider injects its
# default instructions plus exposes six file_access_* tools to the
# agent for the duration of each run.
file_access = FileAccessProvider(store=FileSystemAgentFileStore(working_dir))
# 4. Create the agent and attach the provider. The file-access tools all
# require approval (approval_mode="always_require"). Developers can
# present these to the user for approval, or like in this case, auto-approve
# them via FileAccessProvider.all_tools_auto_approval_rule. Note that
# to use tool approval rules, the agent must have ToolApprovalMiddleware
# in its middleware stack.
async with Agent(
client=client,
name="DataAnalyst",
description="A data analyst assistant that reads, analyzes, and processes data files.",
instructions=INSTRUCTIONS,
context_providers=[file_access],
middleware=[ToolApprovalMiddleware(auto_approval_rules=[FileAccessProvider.all_tools_auto_approval_rule])],
) as agent:
# 5. Run all prompts inside one session so the conversation remains
# coherent across turns.
session = agent.create_session()
for prompt in PROMPTS:
print(f"\nUser: {prompt}")
response = await agent.run(prompt, session=session)
print(f"Assistant: {response}")
# 6. Show the final folder contents so the side effects of the run are
# visible to the reader.
print("\nFinal contents of working/:")
for path in sorted(working_dir.iterdir()):
print(f" - {path.name} ({path.stat().st_size} bytes)")
if __name__ == "__main__":
asyncio.run(main())
# Sample output (truncated):
#
# User: What files do you have access to?
# Assistant: I can see one file in the working directory: sales.csv.
#
# User: Read sales.csv and summarize what columns it contains and how many rows it has.
# Assistant: sales.csv has 50 data rows and 7 columns: date, product, category,
# quantity, unit_price, region, salesperson.
#
# User: Calculate the total revenue (quantity * unit_price) per region and show the result as a table.
# Assistant:
# | Region | Total Revenue |
# |--------|---------------|
# | North | $X,XXX.XX |
# | South | $X,XXX.XX |
# | West | $X,XXX.XX |
#
# User: Save a markdown report named region_totals.md ...
# Assistant: I wrote region_totals.md to the working folder.
#
# User: List the files again so I can confirm region_totals.md was created.
# Assistant: The working folder now contains: region_totals.md, sales.csv.
#
# Final contents of working/:
# - region_totals.md (NNN bytes)
# - sales.csv (3175 bytes)
@@ -0,0 +1,50 @@
date,product,category,quantity,unit_price,region,salesperson
2025-01-03,Laptop Pro 15,Electronics,2,1299.99,North,Alice
2025-01-05,Ergonomic Chair,Furniture,5,349.50,South,Bob
2025-01-07,Wireless Mouse,Electronics,12,24.99,North,Alice
2025-01-08,Standing Desk,Furniture,1,599.00,West,Carol
2025-01-10,USB-C Hub,Electronics,8,45.99,North,David
2025-01-12,Monitor 27in,Electronics,3,429.00,South,Bob
2025-01-14,Desk Lamp,Furniture,6,79.95,West,Carol
2025-01-15,Keyboard Mech,Electronics,4,149.99,North,Alice
2025-01-17,Filing Cabinet,Furniture,2,189.00,South,David
2025-01-20,Webcam HD,Electronics,10,89.99,West,Bob
2025-01-22,Laptop Pro 15,Electronics,1,1299.99,South,Carol
2025-01-24,Ergonomic Chair,Furniture,3,349.50,North,Alice
2025-01-25,Notebook Pack,Stationery,20,12.99,South,David
2025-01-27,Wireless Mouse,Electronics,15,24.99,West,Carol
2025-01-28,Whiteboard,Stationery,4,129.00,North,Bob
2025-01-30,Standing Desk,Furniture,2,599.00,South,Alice
2025-02-02,USB-C Hub,Electronics,6,45.99,West,David
2025-02-04,Monitor 27in,Electronics,2,429.00,North,Carol
2025-02-05,Desk Lamp,Furniture,8,79.95,South,Bob
2025-02-07,Keyboard Mech,Electronics,5,149.99,West,Alice
2025-02-09,Filing Cabinet,Furniture,1,189.00,North,David
2025-02-11,Webcam HD,Electronics,7,89.99,South,Carol
2025-02-13,Laptop Pro 15,Electronics,3,1299.99,West,Bob
2025-02-15,Notebook Pack,Stationery,30,12.99,North,Alice
2025-02-17,Ergonomic Chair,Furniture,4,349.50,South,David
2025-02-19,Wireless Mouse,Electronics,20,24.99,North,Carol
2025-02-20,Whiteboard,Stationery,2,129.00,West,Bob
2025-02-22,Standing Desk,Furniture,1,599.00,North,Alice
2025-02-24,USB-C Hub,Electronics,10,45.99,South,David
2025-02-26,Monitor 27in,Electronics,4,429.00,West,Carol
2025-02-28,Desk Lamp,Furniture,3,79.95,North,Bob
2025-03-02,Keyboard Mech,Electronics,6,149.99,South,Alice
2025-03-04,Filing Cabinet,Furniture,3,189.00,West,David
2025-03-06,Webcam HD,Electronics,9,89.99,North,Carol
2025-03-08,Laptop Pro 15,Electronics,2,1299.99,South,Bob
2025-03-10,Notebook Pack,Stationery,25,12.99,West,Alice
2025-03-12,Ergonomic Chair,Furniture,6,349.50,North,David
2025-03-14,Wireless Mouse,Electronics,18,24.99,South,Carol
2025-03-15,Whiteboard,Stationery,5,129.00,North,Bob
2025-03-17,Standing Desk,Furniture,3,599.00,West,Alice
2025-03-19,USB-C Hub,Electronics,7,45.99,North,David
2025-03-21,Monitor 27in,Electronics,5,429.00,South,Carol
2025-03-23,Desk Lamp,Furniture,4,79.95,West,Bob
2025-03-25,Keyboard Mech,Electronics,3,149.99,North,Alice
2025-03-27,Filing Cabinet,Furniture,2,189.00,South,David
2025-03-28,Webcam HD,Electronics,11,89.99,West,Carol
2025-03-29,Laptop Pro 15,Electronics,1,1299.99,North,Bob
2025-03-30,Notebook Pack,Stationery,15,12.99,South,Alice
2025-03-31,Ergonomic Chair,Furniture,2,349.50,West,David
1 date product category quantity unit_price region salesperson
2 2025-01-03 Laptop Pro 15 Electronics 2 1299.99 North Alice
3 2025-01-05 Ergonomic Chair Furniture 5 349.50 South Bob
4 2025-01-07 Wireless Mouse Electronics 12 24.99 North Alice
5 2025-01-08 Standing Desk Furniture 1 599.00 West Carol
6 2025-01-10 USB-C Hub Electronics 8 45.99 North David
7 2025-01-12 Monitor 27in Electronics 3 429.00 South Bob
8 2025-01-14 Desk Lamp Furniture 6 79.95 West Carol
9 2025-01-15 Keyboard Mech Electronics 4 149.99 North Alice
10 2025-01-17 Filing Cabinet Furniture 2 189.00 South David
11 2025-01-20 Webcam HD Electronics 10 89.99 West Bob
12 2025-01-22 Laptop Pro 15 Electronics 1 1299.99 South Carol
13 2025-01-24 Ergonomic Chair Furniture 3 349.50 North Alice
14 2025-01-25 Notebook Pack Stationery 20 12.99 South David
15 2025-01-27 Wireless Mouse Electronics 15 24.99 West Carol
16 2025-01-28 Whiteboard Stationery 4 129.00 North Bob
17 2025-01-30 Standing Desk Furniture 2 599.00 South Alice
18 2025-02-02 USB-C Hub Electronics 6 45.99 West David
19 2025-02-04 Monitor 27in Electronics 2 429.00 North Carol
20 2025-02-05 Desk Lamp Furniture 8 79.95 South Bob
21 2025-02-07 Keyboard Mech Electronics 5 149.99 West Alice
22 2025-02-09 Filing Cabinet Furniture 1 189.00 North David
23 2025-02-11 Webcam HD Electronics 7 89.99 South Carol
24 2025-02-13 Laptop Pro 15 Electronics 3 1299.99 West Bob
25 2025-02-15 Notebook Pack Stationery 30 12.99 North Alice
26 2025-02-17 Ergonomic Chair Furniture 4 349.50 South David
27 2025-02-19 Wireless Mouse Electronics 20 24.99 North Carol
28 2025-02-20 Whiteboard Stationery 2 129.00 West Bob
29 2025-02-22 Standing Desk Furniture 1 599.00 North Alice
30 2025-02-24 USB-C Hub Electronics 10 45.99 South David
31 2025-02-26 Monitor 27in Electronics 4 429.00 West Carol
32 2025-02-28 Desk Lamp Furniture 3 79.95 North Bob
33 2025-03-02 Keyboard Mech Electronics 6 149.99 South Alice
34 2025-03-04 Filing Cabinet Furniture 3 189.00 West David
35 2025-03-06 Webcam HD Electronics 9 89.99 North Carol
36 2025-03-08 Laptop Pro 15 Electronics 2 1299.99 South Bob
37 2025-03-10 Notebook Pack Stationery 25 12.99 West Alice
38 2025-03-12 Ergonomic Chair Furniture 6 349.50 North David
39 2025-03-14 Wireless Mouse Electronics 18 24.99 South Carol
40 2025-03-15 Whiteboard Stationery 5 129.00 North Bob
41 2025-03-17 Standing Desk Furniture 3 599.00 West Alice
42 2025-03-19 USB-C Hub Electronics 7 45.99 North David
43 2025-03-21 Monitor 27in Electronics 5 429.00 South Carol
44 2025-03-23 Desk Lamp Furniture 4 79.95 West Bob
45 2025-03-25 Keyboard Mech Electronics 3 149.99 North Alice
46 2025-03-27 Filing Cabinet Furniture 2 189.00 South David
47 2025-03-28 Webcam HD Electronics 11 89.99 West Carol
48 2025-03-29 Laptop Pro 15 Electronics 1 1299.99 North Bob
49 2025-03-30 Notebook Pack Stationery 15 12.99 South Alice
50 2025-03-31 Ergonomic Chair Furniture 2 349.50 West David
@@ -0,0 +1,47 @@
# Mem0 Context Provider Examples
[Mem0](https://mem0.ai/) is a self-improving memory layer for Large Language Models that enables applications to have long-term memory capabilities. The Agent Framework's Mem0 context provider integrates with Mem0's API to provide persistent memory across conversation sessions.
This folder contains examples demonstrating how to use the Mem0 context provider with the Agent Framework for persistent memory and context management across conversations.
## Examples
| File | Description |
|------|-------------|
| [`mem0_basic.py`](mem0_basic.py) | Basic example of using Mem0 context provider to store and retrieve user preferences across different conversation threads. |
| [`mem0_sessions.py`](mem0_sessions.py) | Example demonstrating different memory scoping strategies with Mem0. Covers user-scoped memory (memories shared across all sessions for the same user), agent-scoped memory (memories isolated per agent), and multiple agents with different memory configurations for personal vs. work contexts. |
| [`mem0_oss.py`](mem0_oss.py) | Example of using the Mem0 Open Source self-hosted version as the context provider. Demonstrates setup and configuration for local deployment. |
## Prerequisites
### Required Resources
1. [Mem0 API Key](https://app.mem0.ai/) - Sign up for a Mem0 account and get your API key - _or_ self-host [Mem0 Open Source](https://docs.mem0.ai/open-source/overview)
2. Azure AI project endpoint (used in these examples)
3. Azure CLI authentication (run `az login`)
## Configuration
### Environment Variables
Set the following environment variables:
**For Mem0 Platform:**
- `MEM0_API_KEY`: Your Mem0 API key (alternatively, pass it as `api_key` parameter to `Mem0Provider`). Not required if you are self-hosting [Mem0 Open Source](https://docs.mem0.ai/open-source/overview)
**For Mem0 Open Source:**
- `OPENAI_API_KEY`: Your OpenAI API key (used by Mem0 OSS for embedding generation and automatic memory extraction)
**For Azure AI:**
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI project endpoint
- `FOUNDRY_MODEL`: The name of your model deployment
## Key Concepts
### Memory Scoping
The Mem0 context provider supports scoping via identifiers:
- **User scope** (`user_id`): Associate memories with a specific user, shared across all sessions
- **Agent scope** (`agent_id`): Isolate memories per agent persona
- **Application scope** (`application_id`): Associate memories with an application context
@@ -0,0 +1,84 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import uuid
from agent_framework import Agent, tool
from agent_framework.foundry import FoundryChatClient
from agent_framework.mem0 import Mem0ContextProvider
from azure.identity.aio import AzureCliCredential
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
# see samples/02-agents/tools/function_tool_with_approval.py
# and samples/02-agents/tools/function_tool_with_approval_and_sessions.py.
@tool(approval_mode="never_require")
def retrieve_company_report(company_code: str, detailed: bool) -> str:
if company_code != "CNTS":
raise ValueError("Company code not found")
if not detailed:
return "CNTS is a company that specializes in technology."
return (
"CNTS is a company that specializes in technology. "
"It had a revenue of $10 million in 2022. It has 100 employees."
)
async def main() -> None:
"""Example of memory usage with Mem0 context provider."""
print("=== Mem0 Context Provider Example ===")
# Each record in Mem0 should be associated with agent_id or user_id or application_id.
# In this example, we associate Mem0 records with user_id.
user_id = str(uuid.uuid4())
# For Azure authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option.
# For Mem0 authentication, set Mem0 API key via "api_key" parameter or MEM0_API_KEY environment variable.
async with (
AzureCliCredential() as credential,
Agent(
client=FoundryChatClient(credential=credential),
name="FriendlyAssistant",
instructions="You are a friendly assistant.",
tools=retrieve_company_report,
context_providers=[Mem0ContextProvider(source_id="mem0", user_id=user_id)],
) as agent,
):
# First ask the agent to retrieve a company report with no previous context.
# The agent will not be able to invoke the tool, since it doesn't know
# the company code or the report format, so it should ask for clarification.
query = "Please retrieve my company report"
print(f"User: {query}")
result = await agent.run(query)
print(f"Agent: {result}\n")
# Now tell the agent the company code and the report format that you want to use
# and it should be able to invoke the tool and return the report.
query = "I always work with CNTS and I always want a detailed report format. Please remember and retrieve it."
print(f"User: {query}")
result = await agent.run(query)
print(f"Agent: {result}\n")
# Mem0 processes and indexes memories asynchronously.
# Wait for memories to be indexed before querying in a new thread.
# In production, consider implementing retry logic or using Mem0's
# eventual consistency handling instead of a fixed delay.
print("Waiting for memories to be processed...")
await asyncio.sleep(15) # Empirically determined delay for Mem0 indexing
print("\nRequest within a new session:")
# Create a new session for the agent.
# The new session has no context of the previous conversation.
session = agent.create_session()
# Since we have the mem0 component in the session, the agent should be able to
# retrieve the company report without asking for clarification, as it will
# be able to remember the user preferences from Mem0 component.
query = "Please retrieve my company report"
print(f"User: {query}")
result = await agent.run(query, session=session)
print(f"Agent: {result}")
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,74 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import uuid
from agent_framework import Agent, tool
from agent_framework.foundry import FoundryChatClient
from agent_framework.mem0 import Mem0ContextProvider
from azure.identity.aio import AzureCliCredential
from dotenv import load_dotenv
from mem0 import AsyncMemory
# Load environment variables from .env file
load_dotenv()
# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
# see samples/02-agents/tools/function_tool_with_approval.py
# and samples/02-agents/tools/function_tool_with_approval_and_sessions.py.
@tool(approval_mode="never_require")
def retrieve_company_report(company_code: str, detailed: bool) -> str:
if company_code != "CNTS":
raise ValueError("Company code not found")
if not detailed:
return "CNTS is a company that specializes in technology."
return (
"CNTS is a company that specializes in technology. "
"It had a revenue of $10 million in 2022. It has 100 employees."
)
async def main() -> None:
"""Example of memory usage with local Mem0 OSS context provider."""
print("=== Mem0 Context Provider Example ===")
# Each record in Mem0 should be associated with agent_id or user_id or application_id.
# In this example, we associate Mem0 records with user_id.
user_id = str(uuid.uuid4())
# For Azure authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option.
# By default, local Mem0 authenticates to your OpenAI using the OPENAI_API_KEY environment variable.
# See the Mem0 documentation for other LLM providers and authentication options.
local_mem0_client = AsyncMemory()
async with (
AzureCliCredential() as credential,
Agent(
client=FoundryChatClient(credential=credential),
name="FriendlyAssistant",
instructions="You are a friendly assistant.",
tools=retrieve_company_report,
context_providers=[Mem0ContextProvider(source_id="mem0", user_id=user_id, mem0_client=local_mem0_client)],
) as agent,
):
# First ask the agent to retrieve a company report with no previous context.
# The agent will not be able to invoke the tool, since it doesn't know
# the company code or the report format, so it should ask for clarification.
query = "Please retrieve my company report"
print(f"User: {query}")
result = await agent.run(query)
print(f"Agent: {result}\n")
# Now tell the agent the company code and the report format that you want to use
# and it should be able to invoke the tool and return the report.
query = "I always work with CNTS and I always want a detailed report format. Please remember and retrieve it."
print("\nRequest within a new session:")
# Create a new session for the agent.
# The new session has no context of the previous conversation.
session = agent.create_session()
# Since we have the mem0 component in the session, the agent should be able to
# retrieve the company report without asking for clarification, as it will
# be able to remember the user preferences from Mem0 component.
result = await agent.run(query, session=session)
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,170 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
from agent_framework import Agent, tool
from agent_framework.foundry import FoundryChatClient
from agent_framework.mem0 import Mem0ContextProvider
from azure.identity.aio import AzureCliCredential
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
# see samples/02-agents/tools/function_tool_with_approval.py
# and samples/02-agents/tools/function_tool_with_approval_and_sessions.py.
@tool(approval_mode="never_require")
def get_user_preferences(user_id: str) -> str:
"""Mock function to get user preferences."""
preferences = {
"user123": "Prefers concise responses and technical details",
"user456": "Likes detailed explanations with examples",
}
return preferences.get(user_id, "No specific preferences found")
async def example_user_scoped_memory() -> None:
"""Example 1: User-scoped memory (memories shared across all sessions for the same user)."""
print("1. User-Scoped Memory Example:")
print("-" * 40)
user_id = "user123"
async with (
AzureCliCredential() as credential,
Agent(
client=FoundryChatClient(credential=credential),
name="UserMemoryAssistant",
instructions="You are an assistant that remembers user preferences across conversations.",
tools=get_user_preferences,
context_providers=[
Mem0ContextProvider(
source_id="mem0",
user_id=user_id,
)
],
) as user_agent,
):
# Store some preferences
query = "Remember that I prefer technical responses with code examples when discussing programming."
print(f"User: {query}")
result = await user_agent.run(query)
print(f"Agent: {result}\n")
# Create a new session - memories should still be accessible via user_id scoping
new_session = user_agent.create_session()
query = "What do you know about my preferences?"
print(f"User (new session): {query}")
result = await user_agent.run(query, session=new_session)
print(f"Agent: {result}\n")
async def example_agent_scoped_memory() -> None:
"""Example 2: Agent-scoped memory (memories isolated per agent_id).
Note: Use different agent_id values to isolate memories between different
agent personas, even when the user_id is the same.
"""
print("2. Agent-Scoped Memory Example:")
print("-" * 40)
async with (
AzureCliCredential() as credential,
Agent(
client=FoundryChatClient(credential=credential),
name="ScopedMemoryAssistant",
instructions="You are an assistant with agent-scoped memory.",
tools=get_user_preferences,
context_providers=[
Mem0ContextProvider(
source_id="mem0",
agent_id="scoped_assistant",
)
],
) as scoped_agent,
):
query = (
"Remember that I'm working on a Python project about data analysis "
"and I prefer using pandas and matplotlib."
)
print(f"User: {query}")
result = await scoped_agent.run(query)
print(f"Agent: {result}\n")
new_session = scoped_agent.create_session()
query = "What do you know about my current project and preferences?"
print(f"User (new session): {query}")
result = await scoped_agent.run(query, session=new_session)
print(f"Agent: {result}\n")
async def example_multiple_agents() -> None:
"""Example 3: Multiple agents with different memory configurations."""
print("3. Multiple Agents with Different Memory Configurations:")
print("-" * 40)
agent_id_1 = "agent_personal"
agent_id_2 = "agent_work"
async with (
AzureCliCredential() as credential,
Agent(
client=FoundryChatClient(credential=credential),
name="PersonalAssistant",
instructions="You are a personal assistant that helps with personal tasks.",
context_providers=[
Mem0ContextProvider(
source_id="mem0",
agent_id=agent_id_1,
)
],
) as personal_agent,
Agent(
client=FoundryChatClient(credential=credential),
name="WorkAssistant",
instructions="You are a work assistant that helps with professional tasks.",
context_providers=[
Mem0ContextProvider(
source_id="mem0",
agent_id=agent_id_2,
)
],
) as work_agent,
):
# Store personal information
query = "Remember that I like to exercise at 6 AM and prefer outdoor activities."
print(f"User to Personal Agent: {query}")
result = await personal_agent.run(query)
print(f"Personal Agent: {result}\n")
# Store work information
query = "Remember that I have team meetings every Tuesday at 2 PM."
print(f"User to Work Agent: {query}")
result = await work_agent.run(query)
print(f"Work Agent: {result}\n")
# Test memory isolation
query = "What do you know about my schedule?"
print(f"User to Personal Agent: {query}")
result = await personal_agent.run(query)
print(f"Personal Agent: {result}\n")
print(f"User to Work Agent: {query}")
result = await work_agent.run(query)
print(f"Work Agent: {result}\n")
async def main() -> None:
"""Run all Mem0 memory management examples."""
print("=== Mem0 Memory Management Example ===\n")
await example_user_scoped_memory()
await example_agent_scoped_memory()
await example_multiple_agents()
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,19 @@
# Neo4j Context Providers
Neo4j offers two context providers for the Agent Framework, each serving a different purpose:
| | [Neo4j Memory](../neo4j_memory/README.md) | [Neo4j GraphRAG](../../../05-end-to-end/neo4j_graphrag/README.md) |
|---|---|---|
| **What it does** | Read-write memory — stores conversations, builds knowledge graphs, learns from interactions | Read-only retrieval from a pre-existing knowledge base with optional graph traversal |
| **Data source** | Agent interactions (grows over time) | Pre-loaded documents and indexes |
| **Python package** | [`neo4j-agent-memory`](https://pypi.org/project/neo4j-agent-memory/) | [`agent-framework-neo4j`](https://pypi.org/project/agent-framework-neo4j/) |
| **Database setup** | Empty — creates its own schema | Requires pre-indexed documents with vector or fulltext indexes |
| **Example use case** | "Remember my preferences", "What did we discuss last time?" | "Search our documents", "What risks does Acme Corp face?" |
## Which should I use?
**Use [Neo4j Memory](../neo4j_memory/README.md)** when your agent needs to remember things across sessions — user preferences, past conversations, extracted entities, and reasoning traces. The memory provider writes to the database on every interaction, building a knowledge graph that grows over time.
**Use [Neo4j GraphRAG](../../../05-end-to-end/neo4j_graphrag/README.md)** when your agent needs to search an existing knowledge base — documents, articles, product catalogs — and optionally enrich results by traversing graph relationships. The GraphRAG provider is read-only and does not modify your data.
You can use both together: GraphRAG for domain knowledge retrieval, Memory for personalization and learning.
@@ -0,0 +1,9 @@
# Neo4j Memory Context Provider
[Neo4j Agent Memory](https://github.com/neo4j-labs/agent-memory) is a graph-native memory system for AI agents that stores conversations, builds knowledge graphs from interactions, and lets agents learn from their own reasoning — all backed by Neo4j.
For full documentation, installation instructions, code examples, and configuration details, see the [Neo4j Memory integration guide on Microsoft Learn](https://learn.microsoft.com/agent-framework/integrations/neo4j-memory).
For a runnable example, see the [retail assistant sample](https://github.com/neo4j-labs/agent-memory/tree/main/examples/microsoft_agent_retail_assistant).
For help choosing between the Memory and GraphRAG providers, see the [Neo4j Context Providers overview](../neo4j/README.md).
@@ -0,0 +1,123 @@
# Redis Context Provider Examples
The Redis context provider enables persistent, searchable memory for your agents using Redis (RediSearch). It supports fulltext search and optional hybrid search with vector embeddings, letting agents remember and retrieve user context across sessions and threads.
This folder contains an example demonstrating how to use the Redis context provider with the Agent Framework.
## Examples
| File | Description |
|------|-------------|
| [`azure_redis_conversation.py`](azure_redis_conversation.py) | Demonstrates conversation persistence with RedisHistoryProvider and Azure Redis with Azure AD (Entra ID) authentication using credential provider. |
| [`redis_basics.py`](redis_basics.py) | Shows standalone provider usage and agent integration. Demonstrates writing messages to Redis, retrieving context via fulltext or hybrid vector search, and persisting preferences across threads. Also includes a simple tool example whose outputs are remembered. |
| [`redis_conversation.py`](redis_conversation.py) | Simple example showing conversation persistence with RedisContextProvider using traditional connection string authentication. |
| [`redis_sessions.py`](redis_sessions.py) | Demonstrates memory scoping strategies. Includes: (1) global memory scope with `application_id`, `agent_id`, and `user_id` shared across operations; (2) hybrid vector search using a custom OpenAI vectorizer for richer context retrieval; and (3) multiple agents with isolated memory via different `agent_id` values. |
## Prerequisites
### Required resources
1. A running Redis with RediSearch (Redis Stack or a managed service)
2. Python environment with Agent Framework Redis extra installed
3. Azure AI Foundry project endpoint and Azure OpenAI Responses deployment
4. Optional: OpenAI API key if using vector embeddings
### Install the package
```bash
pip install "agent-framework-redis"
```
## Running Redis
Pick one option:
### Option A: Docker (local Redis Stack)
```bash
docker run --name redis -p 6379:6379 -d redis:8.0.3
```
### Option B: Redis Cloud
Create a free database and get the connection URL at `https://redis.io/cloud/`.
### Option C: Azure Managed Redis
See quickstart: `https://learn.microsoft.com/azure/redis/quickstart-create-managed-redis`
## Configuration
### Environment variables
- `FOUNDRY_PROJECT_ENDPOINT` (required): Azure AI Foundry project endpoint for `FoundryChatClient`
- `FOUNDRY_MODEL` (required): Foundry model deployment name
- `OPENAI_API_KEY` (optional): Required only if you set `vectorizer_choice="openai"` to enable hybrid search.
### Provider configuration highlights
The provider supports both fulltext only and hybrid vector search:
- Set `vectorizer_choice` to `"openai"` or `"hf"` to enable embeddings and hybrid search.
- When using a vectorizer, also set `vector_field_name` (e.g., `"vector"`).
- Partition fields for scoping memory: `application_id`, `agent_id`, `user_id`.
- Index management: `index_name`, `overwrite_redis_index`, `drop_redis_index`.
## What the example does
`redis_basics.py` walks through three scenarios:
1. Standalone provider usage: adds messages and retrieves context via `invoking`.
2. Agent integration: teaches the agent a preference and verifies it is remembered across turns.
3. Agent + tool: calls a sample tool (flight search) and then asks the agent to recall details remembered from the tool output.
It uses `FoundryChatClient` for chat and, in some steps, optional OpenAI embeddings for hybrid search.
## How to run
1) Start Redis (see options above). For local default, ensure it's reachable at `redis://localhost:6379`.
2) Set Azure Foundry/OpenAI responses environment variables:
```bash
export FOUNDRY_PROJECT_ENDPOINT="https://<resource>.services.ai.azure.com/api/projects/<project>"
export FOUNDRY_MODEL="<deployment-name>"
```
3) (Optional) Set your OpenAI key if using embeddings:
```bash
export OPENAI_API_KEY="<your key>"
```
4) Run the example:
```bash
python redis_basics.py
```
You should see the agent responses and, when using embeddings, context retrieved from Redis. The example includes commented debug helpers you can print, such as index info or all stored docs.
## Key concepts
### Memory scoping
- Global scope: set `application_id`, `agent_id`, or `user_id` on the provider to filter memory.
- Agent isolation: use different `agent_id` values to keep memories separated for different agent personas.
### Hybrid vector search (optional)
- Enable by setting `vectorizer_choice` to `"openai"` (requires `OPENAI_API_KEY`) or `"hf"` (offline model).
- Provide `vector_field_name` (e.g., `"vector"`); other vector settings have sensible defaults.
### Index lifecycle controls
- `overwrite_redis_index` and `drop_redis_index` help recreate indexes during iteration.
## Troubleshooting
- Ensure at least one of `application_id`, `agent_id`, or `user_id` is set; the provider requires a scope.
- Verify `FOUNDRY_PROJECT_ENDPOINT` and `FOUNDRY_MODEL` are set for the chat client.
- If using embeddings, verify `OPENAI_API_KEY` is set and reachable.
- Make sure Redis exposes RediSearch (Redis Stack image or managed service with search enabled).
@@ -0,0 +1,140 @@
# Copyright (c) Microsoft. All rights reserved.
"""Azure Managed Redis History Provider with Azure AD Authentication
This example demonstrates how to use Azure Managed Redis with Azure AD authentication
to persist conversation history using RedisHistoryProvider.
Key concepts:
- RedisHistoryProvider = durable storage (where messages are persisted)
- AgentSession = conversation identity (which conversation the messages belong to)
Requirements:
- Azure Managed Redis instance with Azure AD authentication enabled
- Azure credentials configured (az login or managed identity)
- agent-framework-redis: pip install agent-framework-redis
- azure-identity: pip install azure-identity
Environment Variables:
- AZURE_REDIS_HOST: Your Azure Managed Redis host (e.g., myredis.redis.cache.windows.net)
- FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
- FOUNDRY_MODEL: Azure OpenAI Responses deployment name
- AZURE_USER_OBJECT_ID: Your Azure AD User Object ID for authentication
"""
import asyncio
import os
from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from agent_framework.redis import RedisHistoryProvider
from azure.identity import AzureCliCredential
from azure.identity.aio import AzureCliCredential as AsyncAzureCliCredential
from dotenv import load_dotenv
from redis.credentials import CredentialProvider
load_dotenv()
class AzureCredentialProvider(CredentialProvider):
"""Credential provider for Azure AD authentication with Redis Enterprise."""
def __init__(self, azure_credential: AsyncAzureCliCredential, user_object_id: str):
self.azure_credential = azure_credential
self.user_object_id = user_object_id
async def get_credentials_async(self) -> tuple[str] | tuple[str, str]:
"""Get Azure AD token for Redis authentication.
Returns (username, token) where username is the Azure user's Object ID.
"""
token = await self.azure_credential.get_token("https://redis.azure.com/.default")
return (self.user_object_id, token.token)
async def main() -> None:
redis_host = os.environ.get("AZURE_REDIS_HOST")
if not redis_host:
print("ERROR: Set AZURE_REDIS_HOST environment variable")
return
# For Azure Redis with Entra ID, username must be your Object ID
user_object_id = os.environ.get("AZURE_USER_OBJECT_ID")
if not user_object_id:
print("ERROR: Set AZURE_USER_OBJECT_ID environment variable")
print("Get your Object ID from the Azure Portal")
return
# 1. Create Azure CLI credential provider (uses 'az login' credentials)
azure_credential = AsyncAzureCliCredential()
credential_provider = AzureCredentialProvider(azure_credential, user_object_id)
# 2. Create Azure Redis history provider (the durable storage backend)
history_provider = RedisHistoryProvider(
source_id="redis_memory",
credential_provider=credential_provider,
host=redis_host,
port=10000,
ssl=True,
key_prefix="chat_messages",
max_messages=100,
)
# 3. Create chat client
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
# 4. Create agent with Azure Redis history provider
agent = Agent(
client=client,
name="AzureRedisAssistant",
instructions="You are a helpful assistant.",
context_providers=[history_provider],
)
# 5. Create a session to provide conversation identity.
# The session ID is used as the Redis key — all runs sharing the same session
# will read/write the same conversation history in Redis.
session = agent.create_session()
# 6. Conversation — each run passes the same session for continuity
query = "Remember that I enjoy gumbo"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
# Ask the agent to recall the stored preference; it should retrieve from memory
query = "What do I enjoy?"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
query = "What did I say to you just now?"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
query = "Remember that I have a meeting at 3pm tomorrow"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
query = "Tulips are red"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
query = "What was the first thing I said to you this conversation?"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
# Cleanup
await azure_credential.close()
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,281 @@
# Copyright (c) Microsoft. All rights reserved.
"""Redis Context Provider: Basic usage and agent integration
This example demonstrates how to use the Redis context provider to persist and
retrieve conversational memory for agents. It covers three progressively more
realistic scenarios:
1) Standalone provider usage ("basic cache")
- Write messages to Redis and retrieve relevant context using full-text or
hybrid vector search.
2) Agent + provider
- Connect the provider to an agent so the agent can store user preferences
and recall them across turns.
3) Agent + provider + tool memory
- Expose a simple tool to the agent, then verify that details from the tool
outputs are captured and retrievable as part of the agent's memory.
Requirements:
- A Redis instance with RediSearch enabled (e.g., Redis Stack)
- agent-framework with the Redis extra installed: pip install "agent-framework-redis"
- Optionally an OpenAI API key if enabling embeddings for hybrid search
Run:
python redis_basics.py
"""
import asyncio
import os
from agent_framework import Agent, Message, tool
from agent_framework.foundry import FoundryChatClient
from agent_framework.redis import RedisContextProvider
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from redisvl.extensions.cache.embeddings import EmbeddingsCache
from redisvl.utils.vectorize import OpenAITextVectorizer
# Load environment variables from .env file
load_dotenv()
# Default Redis URL for local Redis Stack.
# Override via the REDIS_URL environment variable for remote or authenticated instances.
REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379")
# NOTE: approval_mode="never_require" is for sample brevity.
# Use "always_require" in production; see samples/02-agents/tools/function_tool_with_approval.py
# and samples/02-agents/tools/function_tool_with_approval_and_sessions.py.
@tool(approval_mode="never_require")
def search_flights(origin_airport_code: str, destination_airport_code: str, detailed: bool = False) -> str:
"""Simulated flight-search tool to demonstrate tool memory.
The agent can call this function, and the returned details can be stored
by the Redis context provider. We later ask the agent to recall facts from
these tool results to verify memory is working as expected.
"""
# Minimal static catalog used to simulate a tool's structured output
flights = {
("JFK", "LAX"): {
"airline": "SkyJet",
"duration": "6h 15m",
"price": 325,
"cabin": "Economy",
"baggage": "1 checked bag",
},
("SFO", "SEA"): {
"airline": "Pacific Air",
"duration": "2h 5m",
"price": 129,
"cabin": "Economy",
"baggage": "Carry-on only",
},
("LHR", "DXB"): {
"airline": "EuroWings",
"duration": "6h 50m",
"price": 499,
"cabin": "Business",
"baggage": "2 bags included",
},
}
route = (origin_airport_code.upper(), destination_airport_code.upper())
if route not in flights:
return f"No flights found between {origin_airport_code} and {destination_airport_code}"
flight = flights[route]
if not detailed:
return f"Flights available from {origin_airport_code} to {destination_airport_code}."
return (
f"{flight['airline']} operates flights from {origin_airport_code} to {destination_airport_code}. "
f"Duration: {flight['duration']}. "
f"Price: ${flight['price']}. "
f"Cabin: {flight['cabin']}. "
f"Baggage policy: {flight['baggage']}."
)
def create_chat_client() -> FoundryChatClient:
"""Create a FoundryChatClient using a Foundry project endpoint."""
return FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
async def main() -> None:
"""Walk through provider-only, agent integration, and tool-memory scenarios.
Helpful debugging (uncomment when iterating):
- print(await provider.redis_index.info())
- print(await provider.search_all())
"""
print("1. Standalone provider usage:")
print("-" * 40)
# Create a provider with partition scope and OpenAI embeddings
# Please set OPENAI_API_KEY to use the OpenAI vectorizer.
# For chat responses, also set FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL.
# We attach an embedding vectorizer so the provider can perform hybrid (text + vector)
# retrieval. If you prefer text-only retrieval, instantiate RedisContextProvider without the
# 'vectorizer' and vector_* parameters.
vectorizer = OpenAITextVectorizer(
model="text-embedding-ada-002",
api_config={"api_key": os.getenv("OPENAI_API_KEY")},
cache=EmbeddingsCache(name="openai_embeddings_cache", redis_url=REDIS_URL),
)
# The provider manages persistence and retrieval. application_id/agent_id/user_id
# scope data for multi-tenant separation; thread_id (set later) narrows to a
# specific conversation.
provider = RedisContextProvider(
source_id="redis_context",
redis_url=REDIS_URL,
index_name="redis_basics",
application_id="matrix_of_kermits",
agent_id="agent_kermit",
user_id="kermit",
redis_vectorizer=vectorizer,
vector_field_name="vector",
vector_algorithm="hnsw",
vector_distance_metric="cosine",
)
# Build sample chat messages to persist to Redis
messages = [
Message("user", ["runA CONVO: User Message"]),
Message("assistant", ["runA CONVO: Assistant Message"]),
Message("system", ["runA CONVO: System Message"]),
]
# Use the provider's before_run/after_run API to store and retrieve messages.
# In practice, the agent handles this automatically; this shows the low-level API.
from typing import cast
from agent_framework import AgentSession, SessionContext, SupportsAgentRun
session = AgentSession(session_id="runA")
context = SessionContext(input_messages=messages)
state = session.state
# Store messages via after_run
await provider.after_run(agent=cast(SupportsAgentRun, None), session=session, context=context, state=state)
# Retrieve relevant memories via before_run
query_context = SessionContext(input_messages=[Message("system", ["B: Assistant Message"])])
await provider.before_run(agent=cast(SupportsAgentRun, None), session=session, context=query_context, state=state)
# Inspect retrieved memories that would be injected into instructions
# (Debug-only output so you can verify retrieval works as expected.)
print("Before Run Result:")
print(query_context)
# Drop / delete the provider index in Redis
await provider.redis_index.delete()
# --- Agent + provider: teach and recall a preference ---
print("\n2. Agent + provider: teach and recall a preference")
print("-" * 40)
# Fresh provider for the agent demo (recreates index)
vectorizer = OpenAITextVectorizer(
model="text-embedding-ada-002",
api_config={"api_key": os.getenv("OPENAI_API_KEY")},
cache=EmbeddingsCache(name="openai_embeddings_cache", redis_url=REDIS_URL),
)
# Recreate a clean index so the next scenario starts fresh
provider = RedisContextProvider(
source_id="redis_context",
redis_url=REDIS_URL,
index_name="redis_basics_2",
prefix="context_2",
application_id="matrix_of_kermits",
agent_id="agent_kermit",
user_id="kermit",
redis_vectorizer=vectorizer,
vector_field_name="vector",
vector_algorithm="hnsw",
vector_distance_metric="cosine",
)
# Create chat client for the agent
client = create_chat_client()
# Create agent wired to the Redis context provider. The provider automatically
# persists conversational details and surfaces relevant context on each turn.
agent = Agent(
client=client,
name="MemoryEnhancedAssistant",
instructions=(
"You are a helpful assistant. Personalize replies using provided context. "
"Before answering, always check for stored context"
),
tools=[],
context_providers=[provider],
)
# Teach a user preference; the agent writes this to the provider's memory
query = "Remember that I enjoy glugenflorgle"
result = await agent.run(query)
print("User: ", query)
print("Agent: ", result)
# Ask the agent to recall the stored preference; it should retrieve from memory
query = "What do I enjoy?"
result = await agent.run(query)
print("User: ", query)
print("Agent: ", result)
# Drop / delete the provider index in Redis
await provider.redis_index.delete()
# --- Agent + provider + tool: store and recall tool-derived context ---
print("\n3. Agent + provider + tool: store and recall tool-derived context")
print("-" * 40)
# Text-only provider (full-text search only). Omits vectorizer and related params.
provider = RedisContextProvider(
source_id="redis_context",
redis_url=REDIS_URL,
index_name="redis_basics_3",
prefix="context_3",
application_id="matrix_of_kermits",
agent_id="agent_kermit",
user_id="kermit",
)
# Create agent exposing the flight search tool. Tool outputs are captured by the
# provider and become retrievable context for later turns.
client = create_chat_client()
agent = Agent(
client=client,
name="MemoryEnhancedAssistant",
instructions=(
"You are a helpful assistant. Personalize replies using provided context. "
"Before answering, always check for stored context"
),
tools=search_flights,
context_providers=[provider],
)
# Invoke the tool; outputs become part of memory/context
query = "Are there any flights from new york city (jfk) to la? Give me details"
result = await agent.run(query)
print("User: ", query)
print("Agent: ", result)
# Verify the agent can recall tool-derived context
query = "Which flight did I ask about?"
result = await agent.run(query)
print("User: ", query)
print("Agent: ", result)
# Drop / delete the provider index in Redis
await provider.redis_index.delete()
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,124 @@
# Copyright (c) Microsoft. All rights reserved.
"""Redis Context Provider: Basic usage and agent integration
This example demonstrates how to use the Redis context provider to persist
conversational details. Pass it as a constructor argument to create_agent.
Note: For session history persistence, see RedisHistoryProvider in the
conversations/redis_history_provider.py sample. RedisContextProvider is for
AI context (RAG, memories), while RedisHistoryProvider stores message history.
Requirements:
- A Redis instance with RediSearch enabled (e.g., Redis Stack)
- agent-framework with the Redis extra installed: pip install "agent-framework-redis"
- Optionally an OpenAI API key if enabling embeddings for hybrid search
Run:
python redis_conversation.py
"""
import asyncio
import os
from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from agent_framework.redis import RedisContextProvider
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from redisvl.extensions.cache.embeddings import EmbeddingsCache
from redisvl.utils.vectorize import OpenAITextVectorizer
load_dotenv()
# Default Redis URL for local Redis Stack.
# Override via the REDIS_URL environment variable for remote or authenticated instances.
REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379")
async def main() -> None:
"""Walk through provider and chat message store usage.
Helpful debugging (uncomment when iterating):
- print(await provider.redis_index.info())
- print(await provider.search_all())
"""
vectorizer = OpenAITextVectorizer(
model="text-embedding-ada-002",
api_config={"api_key": os.getenv("OPENAI_API_KEY")},
cache=EmbeddingsCache(name="openai_embeddings_cache", redis_url=REDIS_URL),
)
provider = RedisContextProvider(
source_id="redis_context",
redis_url=REDIS_URL,
index_name="redis_conversation",
prefix="redis_conversation",
application_id="matrix_of_kermits",
agent_id="agent_kermit",
user_id="kermit",
redis_vectorizer=vectorizer,
vector_field_name="vector",
vector_algorithm="hnsw",
vector_distance_metric="cosine",
)
# Create chat client for the agent
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
# Create agent wired to the Redis context provider. The provider automatically
# persists conversational details and surfaces relevant context on each turn.
agent = Agent(
client=client,
name="MemoryEnhancedAssistant",
instructions=(
"You are a helpful assistant. Personalize replies using provided context. "
"Before answering, always check for stored context"
),
tools=[],
context_providers=[provider],
)
# Create a session to manage conversation state
session = agent.create_session()
# Teach a user preference; the agent writes this to the provider's memory
query = "Remember that I enjoy gumbo"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
# Ask the agent to recall the stored preference; it should retrieve from memory
query = "What do I enjoy?"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
query = "What did I say to you just now?"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
query = "Remember that I have a meeting at 3pm tomorro"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
query = "Tulips are red"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
query = "What was the first thing I said to you this conversation?"
result = await agent.run(query, session=session)
print("User: ", query)
print("Agent: ", result)
# Drop / delete the provider index in Redis
await provider.redis_index.delete()
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,257 @@
# Copyright (c) Microsoft. All rights reserved.
"""Redis Context Provider: Memory scoping examples
This sample demonstrates how conversational memory can be scoped when using the
Redis context provider. It covers three scenarios:
1) Global memory scope
- Use application_id, agent_id, and user_id to share memories across
all operations/sessions.
2) Hybrid vector search
- Use a custom OpenAI vectorizer with the provider for hybrid vector search.
Demonstrates combining full-text and semantic search for richer context
retrieval.
3) Multiple agents with isolated memory
- Use different agent_id values to keep memories separated for different
agent personas, even when the user_id is the same.
Requirements:
- A Redis instance with RediSearch enabled (e.g., Redis Stack)
- agent-framework with the Redis extra installed: pip install "agent-framework-redis"
- Optionally an OpenAI API key for the chat client in this demo
Run:
python redis_sessions.py
"""
import asyncio
import os
from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from agent_framework.redis import RedisContextProvider
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from redisvl.extensions.cache.embeddings import EmbeddingsCache
from redisvl.utils.vectorize import OpenAITextVectorizer
# Load environment variables from .env file
load_dotenv()
# Default Redis URL for local Redis Stack.
# Override via the REDIS_URL environment variable for remote or authenticated instances.
REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379")
# Please set OPENAI_API_KEY to use the OpenAI vectorizer.
# For chat responses, also set FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL.
def create_chat_client() -> FoundryChatClient:
"""Create a FoundryChatClient using a Foundry project endpoint."""
return FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
async def example_global_memory_scope() -> None:
"""Example 1: Global memory scope (memories shared across all operations)."""
print("1. Global Memory Scope Example:")
print("-" * 40)
client = create_chat_client()
provider = RedisContextProvider(
source_id="redis_context",
redis_url=REDIS_URL,
index_name="redis_threads_global",
application_id="threads_demo_app",
agent_id="threads_demo_agent",
user_id="threads_demo_user",
)
agent = Agent(
client=client,
name="GlobalMemoryAssistant",
instructions=(
"You are a helpful assistant. Personalize replies using provided context. "
"Before answering, always check for stored context containing information"
),
tools=[],
context_providers=[provider],
)
# Store a preference in the global scope
query = "Remember that I prefer technical responses with code examples when discussing programming."
print(f"User: {query}")
result = await agent.run(query)
print(f"Agent: {result}\n")
# Create a new session - memories should still be accessible due to global scope
new_session = agent.create_session()
query = "What technical responses do I prefer?"
print(f"User (new session): {query}")
result = await agent.run(query, session=new_session)
print(f"Agent: {result}\n")
# Clean up the Redis index
await provider.redis_index.delete()
async def example_hybrid_vector_search() -> None:
"""Example 2: Hybrid vector search with custom vectorizer.
Demonstrates using a custom OpenAI vectorizer for hybrid vector search,
combining full-text and semantic search for richer context retrieval.
"""
print("2. Hybrid Vector Search Example:")
print("-" * 40)
client = create_chat_client()
vectorizer = OpenAITextVectorizer(
model="text-embedding-ada-002",
api_config={"api_key": os.getenv("OPENAI_API_KEY")},
cache=EmbeddingsCache(name="openai_embeddings_cache", redis_url=REDIS_URL),
)
provider = RedisContextProvider(
source_id="redis_context",
redis_url=REDIS_URL,
index_name="redis_threads_dynamic",
application_id="threads_demo_app",
agent_id="threads_demo_agent",
user_id="threads_demo_user",
redis_vectorizer=vectorizer,
vector_field_name="vector",
vector_algorithm="hnsw",
vector_distance_metric="cosine",
)
agent = Agent(
client=client,
name="HybridSearchAssistant",
instructions="You are an assistant with hybrid vector search for richer context retrieval.",
context_providers=[provider],
)
# Store some information
query = "Remember that for this conversation, I'm working on a Python project about data analysis."
print(f"User: {query}")
result = await agent.run(query)
print(f"Agent: {result}\n")
# Test memory retrieval via hybrid search
query = "What project am I working on?"
print(f"User: {query}")
result = await agent.run(query)
print(f"Agent: {result}\n")
# Store more information
query = "Also remember that I prefer using pandas and matplotlib for this project."
print(f"User: {query}")
result = await agent.run(query)
print(f"Agent: {result}\n")
# Test comprehensive memory retrieval
query = "What do you know about my current project and preferences?"
print(f"User: {query}")
result = await agent.run(query)
print(f"Agent: {result}\n")
# Clean up the Redis index
await provider.redis_index.delete()
async def example_multiple_agents() -> None:
"""Example 3: Multiple agents with different memory configurations (isolated via agent_id) but within 1 index."""
print("3. Multiple Agents with Different Memory Configurations:")
print("-" * 40)
client = create_chat_client()
vectorizer = OpenAITextVectorizer(
model="text-embedding-ada-002",
api_config={"api_key": os.getenv("OPENAI_API_KEY")},
cache=EmbeddingsCache(name="openai_embeddings_cache", redis_url=REDIS_URL),
)
personal_provider = RedisContextProvider(
source_id="redis_context",
redis_url=REDIS_URL,
index_name="redis_threads_agents",
application_id="threads_demo_app",
agent_id="agent_personal",
user_id="threads_demo_user",
redis_vectorizer=vectorizer,
vector_field_name="vector",
vector_algorithm="hnsw",
vector_distance_metric="cosine",
)
personal_agent = Agent(
client=client,
name="PersonalAssistant",
instructions="You are a personal assistant that helps with personal tasks.",
context_providers=[personal_provider],
)
work_provider = RedisContextProvider(
source_id="redis_context",
redis_url=REDIS_URL,
index_name="redis_threads_agents",
application_id="threads_demo_app",
agent_id="agent_work",
user_id="threads_demo_user",
redis_vectorizer=vectorizer,
vector_field_name="vector",
vector_algorithm="hnsw",
vector_distance_metric="cosine",
)
work_agent = Agent(
client=client,
name="WorkAssistant",
instructions="You are a work assistant that helps with professional tasks.",
context_providers=[work_provider],
)
# Store personal information
query = "Remember that I like to exercise at 6 AM and prefer outdoor activities."
print(f"User to Personal Agent: {query}")
result = await personal_agent.run(query)
print(f"Personal Agent: {result}\n")
# Store work information
query = "Remember that I have team meetings every Tuesday at 2 PM."
print(f"User to Work Agent: {query}")
result = await work_agent.run(query)
print(f"Work Agent: {result}\n")
# Test memory isolation
query = "What do you know about my schedule?"
print(f"User to Personal Agent: {query}")
result = await personal_agent.run(query)
print(f"Personal Agent: {result}\n")
print(f"User to Work Agent: {query}")
result = await work_agent.run(query)
print(f"Work Agent: {result}\n")
# Clean up the Redis index (shared)
await work_provider.redis_index.delete()
async def main() -> None:
print("=== Redis Memory Scoping Examples ===\n")
await example_global_memory_scope()
await example_hybrid_vector_search()
await example_multiple_agents()
if __name__ == "__main__":
asyncio.run(main())
@@ -0,0 +1,128 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from contextlib import suppress
from typing import Any
from agent_framework import Agent, AgentSession, ContextProvider, SessionContext, SupportsChatGetResponse
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from pydantic import BaseModel
# Load environment variables from .env file
load_dotenv()
class UserInfo(BaseModel):
name: str | None = None
age: int | None = None
class UserInfoMemory(ContextProvider):
DEFAULT_SOURCE_ID = "user_info_memory"
def __init__(self, source_id: str = DEFAULT_SOURCE_ID, *, client: SupportsChatGetResponse, **kwargs: Any):
"""Create the memory.
If you pass in kwargs, they will be attempted to be used to create a UserInfo object.
"""
super().__init__(source_id)
self._chat_client = client
async def after_run(
self,
*,
agent: Any,
session: AgentSession | None,
context: SessionContext,
state: dict[str, Any],
) -> None:
"""Extract user information from messages after each agent call."""
# ensure you get all the messages you want to parse from, including the input in this case.
request_messages = context.get_messages(include_input=True, include_response=True)
# Check if we need to extract user info from user messages
user_messages = [msg for msg in request_messages if hasattr(msg, "role") and msg.role == "user"] # type: ignore
if (state["user_info"].name is None or state["user_info"].age is None) and user_messages:
with suppress(Exception):
# Use the chat client to extract structured information
result = await self._chat_client.get_response(
messages=request_messages, # type: ignore
options={
"instructions": "Extract the user's name and age from the message if present. "
"If not present return nulls.",
"response_format": UserInfo,
},
)
# Update user info with extracted data
with suppress(Exception):
extracted = result.value
user_info = state["user_info"]
if not isinstance(extracted, UserInfo) or not isinstance(user_info, UserInfo):
return
if user_info.name is None and extracted.name:
user_info.name = extracted.name
if user_info.age is None and extracted.age:
user_info.age = extracted.age
async def before_run(
self,
*,
agent: Any,
session: AgentSession | None,
context: SessionContext,
state: dict[str, Any],
) -> None:
"""Provide user information context before each agent call."""
state.setdefault("user_info", UserInfo())
context.extend_instructions(
self.source_id,
"Ask the user for their name and politely decline to answer any questions until they provide it."
if state["user_info"].name is None
else f"The user's name is {state['user_info'].name}.",
)
context.extend_instructions(
self.source_id,
"Ask the user for their age and politely decline to answer any questions until they provide it."
if state["user_info"].age is None
else f"The user's age is {state['user_info'].age}.",
)
async def main():
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
context_name = UserInfoMemory.DEFAULT_SOURCE_ID
# Create the memory provider
memory_provider = UserInfoMemory(context_name, client=client)
# Create the agent with memory
async with Agent(
client=client,
instructions="You are a friendly assistant. Always address the user by their name.",
context_providers=[memory_provider],
) as agent:
# Create a new session for the conversation
session = agent.create_session()
for msg in ["Hello, what is the square root of 9?", "My name is Ruaidhrí", "I am 20 years old"]:
print(f"User: {msg}")
print(f"Assistant: {await agent.run(msg, session=session)}")
# Access the memory component and inspect the memories
print()
print(f"MEMORY - User Name: {session.state[context_name]['user_info'].name}")
print(f"MEMORY - User Age: {session.state[context_name]['user_info'].age}")
if __name__ == "__main__":
asyncio.run(main())