wehub-resource-sync
fed8b2eed7
Backend release / release (push) Waiting to run
Bandit Security Scan / bandit_scan (push) Waiting to run
Build and push multi-arch DocsGPT Docker image / build (linux/amd64, ubuntu-latest, amd64) (push) Waiting to run
Build and push multi-arch DocsGPT Docker image / build (linux/arm64, ubuntu-24.04-arm, arm64) (push) Waiting to run
Build and push multi-arch DocsGPT Docker image / manifest (push) Blocked by required conditions
Build and push DocsGPT FE Docker image for development / build (linux/amd64, ubuntu-latest, amd64) (push) Waiting to run
Build and push DocsGPT FE Docker image for development / build (linux/arm64, ubuntu-24.04-arm, arm64) (push) Waiting to run
Build and push DocsGPT FE Docker image for development / manifest (push) Blocked by required conditions
Python linting / ruff (push) Waiting to run
Run python tests with pytest / Run tests and count coverage (3.12) (push) Waiting to run
React Widget Build / build (push) Waiting to run
88 lines
4.5 KiB
Plaintext
88 lines
4.5 KiB
Plaintext
# Workflow Nodes
|
|
|
|
DocsGPT workflows are composed of **Nodes** that are connected to form a processing graph. These nodes interact with a **Shared State**—a global dictionary of variables that persists throughout the execution of the workflow.
|
|
|
|
## The Shared State
|
|
|
|
Every workflow run maintains a state object (a JSON-like dictionary).
|
|
- **Initial State**: Contains the user's input query (`{{query}}`) and chat history (`{{chat_history}}`).
|
|
- **Accessing Variables**: You can access any variable in the state using the double-curly braces syntax: `{{variable_name}}`.
|
|
- **Modifying State**: Nodes read from this state and write their outputs back to it.
|
|
|
|
---
|
|
|
|
## AI Agent Node
|
|
|
|
The **AI Agent Node** is the core processing unit. It uses a Large Language Model (LLM) to generate text, answer questions, or perform tasks using tools.
|
|
|
|
### Inputs (Template Variables)
|
|
|
|
The primary input is the **Prompt Template**. This field supports variable substitution.
|
|
|
|
- **Prompt Template**: The text sent to the model.
|
|
- *Example*: `"Summarize the following text: {{user_input_text}}"`
|
|
- If left empty, it defaults to the initial user query (`{{query}}`).
|
|
- **System Prompt**: Instructions that define the agent's persona and constraints.
|
|
- **Tools**: A list of tools the agent can use (e.g., search, calculator).
|
|
- **LLM Settings**: Specific provider, model name, and parameters.
|
|
|
|
### Outputs (Emissions)
|
|
|
|
When the agent completes its task, it stores the result in the shared state.
|
|
|
|
- **Output Variable**: The name of the variable where the result will be saved.
|
|
- *Default*: If not specified, it is saved as `node_{node_id}_output`.
|
|
- *Custom*: You can set this to something meaningful, like `summary` or `translated_text`.
|
|
- **Streaming**: If "Stream to user" is enabled, the output is sent to the user in real-time as it is generated, in addition to being saved to the state.
|
|
|
|
### Documents
|
|
|
|
An agent node can receive documents as inputs. Choose which documents the node sees:
|
|
|
|
- **All**: every document attached to the run.
|
|
- **None**: no documents.
|
|
- **Choose**: a specific set that you select.
|
|
|
|
For how a chosen document reaches the model, the node can pass it natively (send the file to a model that accepts files) or extract it to text first. The default picks automatically based on the model and the file type.
|
|
|
|
---
|
|
|
|
## Set State Node
|
|
|
|
The **Set State Node** allows you to manipulate variables within the shared state directly without calling an LLM. This is useful for initialization, formatting, or control flow logic.
|
|
|
|
### Operations
|
|
|
|
You can define multiple operations in a single node. Each operation targets a specific **Key** (variable name).
|
|
|
|
1. **Set**: Assigns a specific value to a variable.
|
|
- *Value*: Can be a static string or a template using variables.
|
|
- *Example*: Set `current_step` to `1`.
|
|
- *Example*: Set `formatted_response` to `Analysis: {{analysis_result}}`.
|
|
|
|
2. **Increment**: Increases the value of a numeric variable.
|
|
- *Value*: The amount to add (default is 1).
|
|
- *Example*: Increment `retry_count` by `1`.
|
|
|
|
3. **Append**: Adds a value to a list variable.
|
|
- *Value*: The item to add to the list.
|
|
- *Example*: Append `{{last_result}}` to `history_list`.
|
|
|
|
### Usage Examples
|
|
|
|
- **Loop Counters**: Use a *Set State* node to initialize a counter (`i = 0`) before a loop, and another to increment it inside the loop.
|
|
- **Accumulators**: Use *Append* to collect results from multiple parallel branches into a single list.
|
|
- **Renaming**: Copy the output of a previous node to a more generic name (e.g., set `context` to `{{search_results}}`) so subsequent nodes can use a standard variable name.
|
|
|
|
---
|
|
|
|
## Code Node
|
|
|
|
The **Code Node** runs a script in a sandboxed session bound to the workflow run. Use it to transform data, parse files, cross-check documents, or build a report that later nodes consume.
|
|
|
|
- **Code**: the script to run. The workflow state is available to the script as data, so it can read variables, compute, and write results back.
|
|
- **Inputs**: documents or artifacts to place in the workspace before the script runs. Each input accepts a produced artifact reference, a full artifact id, or an attached file.
|
|
- **Outputs**: any files the script writes are captured as artifacts and surfaced in the run view. Write a small JSON value back to the state to pass a decision or summary to later nodes.
|
|
|
|
Runs are sandboxed and have a fixed time limit, so keep each step focused. See [Artifacts and Code Execution](/Tools/artifacts-and-code-execution) for the sandbox backends and configuration.
|