chore: import upstream snapshot with attribution

apps/opik-documentation/python-sdk-docs/source/integrations/adk/OpikTracer.rst

@@ -0,0 +1,5 @@
+OpikTracer
+==========
+
+.. autoclass:: opik.integrations.adk.OpikTracer
+    :members:

apps/opik-documentation/python-sdk-docs/source/integrations/adk/index.rst

@@ -0,0 +1,33 @@
+ADK
+===
+
+Opik integrates with Adk to allow you to log your ADK agent run to the Opik platform, use the `OpikTracer` callback to start logging::
+
+      from google.adk.agents import Agent
+      from opik.integrations.adk import OpikTracer
+
+
+      opik_tracer = OpikTracer()
+
+      root_agent = Agent(
+         name="weather_time_agent",
+         model="gemini-2.0-flash-exp",
+         description=DESCRIPTION,
+         instruction=INSTRUCTION,
+         tools=[...],
+         before_agent_callback=opik_tracer.before_agent_callback,
+         after_agent_callback=opik_tracer.after_agent_callback,
+         before_model_callback=opik_tracer.before_model_callback,
+         after_model_callback=opik_tracer.after_model_callback,
+         before_tool_callback=opik_tracer.before_tool_callback,
+         after_tool_callback=opik_tracer.after_tool_callback,
+      )
+
+You can learn more about the `OpikTracer` object in the following section:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   OpikTracer
+   track_adk_agent_recursive

apps/opik-documentation/python-sdk-docs/source/integrations/adk/track_adk_agent_recursive.rst

@@ -0,0 +1,4 @@
+track_adk_agent_recursive
+=========================
+
+.. autofunction:: opik.integrations.adk.track_adk_agent_recursive

apps/opik-documentation/python-sdk-docs/source/integrations/anthropic/index.rst

@@ -0,0 +1,26 @@
+Anthropic
+=========
+
+Opik integrates with Anthropic to allow you to log your Anthropic calls to the Opik platform, simply wrap the Anthropic client with `track_anthropic` to start logging::
+
+    from opik.integrations.anthropic import track_anthropic
+    from anthropic import Anthropic
+
+    anthropic_client = Anthropic()
+    openai_client = track_openai(openai_client)
+
+    response = anthropic_client.messages.create(
+        model="claude-3-5-sonnet-20241022",
+        max_tokens=1024,
+        messages=[
+            {"role": "user", "content": PROMPT}
+        ]
+    )
+
+You can learn more about the `track_anthropic` decorator in the following section:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   track_anthropic

apps/opik-documentation/python-sdk-docs/source/integrations/anthropic/track_anthropic.rst

@@ -0,0 +1,4 @@
+track_anthropic
+===============
+
+.. autofunction:: opik.integrations.anthropic.track_anthropic

apps/opik-documentation/python-sdk-docs/source/integrations/bedrock/index.rst

@@ -0,0 +1,26 @@
+Bedrock
+=======
+
+Opik integrates with Bedrock to allow you to log your Bedrock calls to the Opik platform, simply wrap the Bedrock client with `track_bedrock` to start logging::
+
+   from opik.integrations.bedrock import track_bedrock
+   import boto3
+
+   bedrock = boto3.client(
+       service_name="bedrock-runtime",
+       region_name=REGION,
+   )
+   bedrock_client = track_bedrock(bedrock, project_name="bedrock-integration-demo")
+
+   response = bedrock_client.converse(
+       modelId=MODEL_ID,
+       messages=[{"role": "user", "content": [{"text": "Hello World!"}]}],
+   )
+
+You can learn more about the `track_bedrock` decorator in the following section:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   track_bedrock

apps/opik-documentation/python-sdk-docs/source/integrations/bedrock/track_bedrock.rst

@@ -0,0 +1,4 @@
+track_bedrock
+=============
+
+.. autofunction:: opik.integrations.bedrock.track_bedrock

apps/opik-documentation/python-sdk-docs/source/integrations/crewai/index.rst

@@ -0,0 +1,65 @@
+CrewAI
+=======
+
+Opik integrates with CrewAI to allow you to log your CrewAI activities and LLM calls to the Opik platform, simply invoke `track_crewai` to start logging::
+
+    from opik.integrations.crewai import track_crewai
+    from crewai import Agent, Crew, Task, Process
+
+
+    class YourCrewName:
+        def agent_one(self) -> Agent:
+            return Agent(
+                role="Data Analyst",
+                goal="Analyze data trends in the market",
+                backstory="An experienced data analyst with a background in economics",
+                verbose=True,
+            )
+
+        def agent_two(self) -> Agent:
+            return Agent(
+                role="Market Researcher",
+                goal="Gather information on market dynamics",
+                backstory="A diligent researcher with a keen eye for detail",
+                verbose=True
+            )
+
+        def task_one(self) -> Task:
+            return Task(
+                name="Collect Data Task",
+                description="Collect recent market data and identify trends.",
+                expected_output="A report summarizing key trends in the market.",
+                agent=self.agent_one()
+            )
+
+        def task_two(self) -> Task:
+            return Task(
+                name="Market Research Task",
+                description="Research factors affecting market dynamics.",
+                expected_output="An analysis of factors influencing the market.",
+                agent=self.agent_two()
+            )
+
+        def crew(self) -> Crew:
+            return Crew(
+                agents=[self.agent_one(), self.agent_two()],
+                tasks=[self.task_one(), self.task_two()],
+                process=Process.sequential,
+                verbose=True
+            )
+
+    track_crewai(project_name="crewai-integration-demo")
+
+    my_crew = YourCrewName().crew()
+    result = my_crew.kickoff()
+
+    print(result)
+
+
+You can learn more about the `track_crewai` decorator in the following section:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   track_crewai

apps/opik-documentation/python-sdk-docs/source/integrations/crewai/track_crewai.rst

@@ -0,0 +1,4 @@
+track_crewai
+=============
+
+.. autofunction:: opik.integrations.crewai.track_crewai

apps/opik-documentation/python-sdk-docs/source/integrations/dspy/OpikCallback.rst

@@ -0,0 +1,5 @@
+OpikCallback
+============
+
+.. autoclass:: opik.integrations.dspy.OpikCallback
+    :members:

apps/opik-documentation/python-sdk-docs/source/integrations/dspy/index.rst

@@ -0,0 +1,32 @@
+DSPy
+====
+
+Opik integrates with DSPy to allow you to log your DSPy runs to the Opik platform::
+
+    import dspy
+    from opik.integrations.dspy.callback import OpikCallback
+
+    project_name = "DSPY"
+
+    lm = dspy.LM(
+        model="openai/gpt-4o-mini",
+    )
+    dspy.configure(lm=lm)
+
+
+    opik_callback = OpikCallback(project_name=project_name, log_graph=True)
+    dspy.settings.configure(
+        callbacks=[opik_callback],
+    )
+
+    cot = dspy.ChainOfThought("question -> answer")
+    cot(question="What is the meaning of life?")
+
+
+You can learn more about the `OpikCallback` in the following section:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   OpikCallback

apps/opik-documentation/python-sdk-docs/source/integrations/guardrails/index.rst

@@ -0,0 +1,44 @@
+Guardrails AI
+=============
+
+Opik integrates with Guardrails AI to allow you to log your activities to the Opik platform, simply invoke `track_guardrails` to start logging.
+
+
+First, install the politeness check from the guardrails hub:
+
+``guardrails hub install hub://guardrails/politeness_check``
+
+
+Then you can run the example:
+::
+
+    from guardrails import Guard, OnFailAction
+    from guardrails.hub import PolitenessCheck
+
+    import opik
+    from opik.integrations.guardrails import track_guardrails
+
+    politeness_check = PolitenessCheck(
+        llm_callable="gpt-3.5-turbo", on_fail=OnFailAction.NOOP
+    )
+
+    guard: Guard = Guard()
+    if hasattr(guard, "use_many"):
+        guard = guard.use_many(politeness_check)
+    else:
+        guard = guard.use(politeness_check)
+    guard = track_guardrails(guard, project_name="guardrails-integration-example")
+
+    result = guard.validate(
+        "Would you be so kind to pass me a cup of tea?",
+    )
+
+Every guardrails check will be logged as a separate trace. Opik will capture inputs, outputs, and provide the trace with a tag "fail" or "pass" for easier management.
+
+You can learn more about the `track_guardrails` decorator in the following section:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   track_guardrails

apps/opik-documentation/python-sdk-docs/source/integrations/guardrails/track_guardrails.rst

@@ -0,0 +1,4 @@
+track_guardrails
+================
+
+.. autofunction:: opik.integrations.guardrails.track_guardrails

apps/opik-documentation/python-sdk-docs/source/integrations/haystack/OpikConnector.rst

@@ -0,0 +1,5 @@
+OpikConnector
+=============
+
+.. autoclass:: opik.integrations.haystack.OpikConnector
+    :members:

apps/opik-documentation/python-sdk-docs/source/integrations/haystack/index.rst

@@ -0,0 +1,53 @@
+Haystack
+========
+
+Opik integrates with Haystack to allow you to log your Haystack pipeline runs to the Opik platform, simply wrap the Haystack pipeline with `OpikConnector` to start logging::
+
+   import os
+
+    os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "true"
+
+    from haystack import Pipeline
+    from haystack.components.builders import ChatPromptBuilder
+    from haystack.components.generators.chat import OpenAIChatGenerator
+    from haystack.dataclasses import ChatMessage
+
+    from opik.integrations.haystack import OpikConnector
+
+
+    pipe = Pipeline()
+
+    # Add the OpikConnector component to the pipeline
+    pipe.add_component(
+        "tracer", OpikConnector("Chat example")
+    )
+
+    # Continue building the pipeline
+    pipe.add_component("prompt_builder", ChatPromptBuilder())
+    pipe.add_component("llm", OpenAIChatGenerator(model="gpt-3.5-turbo"))
+
+    pipe.connect("prompt_builder.prompt", "llm.messages")
+
+    messages = [
+        ChatMessage.from_system(
+            "Always respond in German even if some input data is in other languages."
+        ),
+        ChatMessage.from_user("Tell me about {{location}}"),
+    ]
+
+    response = pipe.run(
+        data={
+            "prompt_builder": {
+                "template_variables": {"location": "Berlin"},
+                "template": messages,
+            }
+        }
+    )
+
+You can learn more about the `OpikConnector` in the following section:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   OpikConnector

apps/opik-documentation/python-sdk-docs/source/integrations/langchain/OpikTracer.rst

@@ -0,0 +1,5 @@
+OpikTracer
+==========
+
+.. autoclass:: opik.integrations.langchain.OpikTracer
+    :members:

apps/opik-documentation/python-sdk-docs/source/integrations/langchain/extract_current_langgraph_span_data.rst

@@ -0,0 +1,5 @@
+extract_current_langgraph_span_data
+===================================
+
+.. autofunction:: opik.integrations.langchain.extract_current_langgraph_span_data
+

apps/opik-documentation/python-sdk-docs/source/integrations/langchain/index.rst

@@ -0,0 +1,36 @@
+langchain
+=========
+
+Opik integrates with Langchain to allow you to log your Langchain calls to the Opik platform, simply wrap the Langchain client with `OpikTracer` to start logging::
+
+   from langchain.chains import LLMChain
+   from langchain_openai import OpenAI
+   from langchain.prompts import PromptTemplate
+   from opik.integrations.langchain import OpikTracer
+
+   # Initialize the tracer
+   opik_tracer = OpikTracer()
+
+   # Create the LLM Chain using LangChain
+   llm = OpenAI(temperature=0)
+
+   prompt_template = PromptTemplate(
+      input_variables=["input"],
+      template="Translate the following text to French: {input}"
+   )
+
+   llm_chain = LLMChain(llm=llm, prompt=prompt_template)
+
+   # Generate the translations
+   translation = llm_chain.run("Hello, how are you?", callbacks=[opik_tracer])
+   print(translation)
+
+You can learn more about the LangChain integration functions in the following sections:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   OpikTracer
+   track_langgraph
+   extract_current_langgraph_span_data

apps/opik-documentation/python-sdk-docs/source/integrations/langchain/track_langgraph.rst

@@ -0,0 +1,5 @@
+track_langgraph
+===============
+
+.. autofunction:: opik.integrations.langchain.track_langgraph
+

apps/opik-documentation/python-sdk-docs/source/integrations/llama_index/LlamaIndexCallbackHandler.rst

@@ -0,0 +1,4 @@
+LlamaIndexCallbackHandler
+=========================
+
+.. autofunction:: opik.integrations.llama_index.LlamaIndexCallbackHandler

apps/opik-documentation/python-sdk-docs/source/integrations/llama_index/index.rst

@@ -0,0 +1,19 @@
+llama_index
+===========
+
+Opik integrates with LlamaIndex to allow you to log your LlamaIndex calls to the Opik platform. To enable the logging to Opik, simply set::
+    
+    from llama_index.core import Settings
+    from llama_index.core.callbacks import CallbackManager
+    from opik.integrations.llama_index import LlamaIndexCallbackHandler
+
+    opik_callback_handler = LlamaIndexCallbackHandler()
+    Settings.callback_manager = CallbackManager([opik_callback_handler])
+
+You can learn more about the `LlamaIndexCallbackHandler` callback in the following section:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   LlamaIndexCallbackHandler

apps/opik-documentation/python-sdk-docs/source/integrations/openai/index.rst

@@ -0,0 +1,22 @@
+openai
+=======
+
+Opik integrates with OpenAI to allow you to log your OpenAI calls to the Opik platform, simply wrap the OpenAI client with `track_openai` to start logging::
+
+   from opik.integrations.openai import track_openai
+   from openai import OpenAI
+
+   openai_client = OpenAI()
+   openai_client = track_openai(openai_client)
+
+   response = openai_client.Completion.create(
+      prompt="Hello, world!",
+   )
+
+You can learn more about the `track_openai` decorator in the following section:
+
+.. toctree::
+   :maxdepth: 4
+   :titlesonly:
+
+   track_openai

apps/opik-documentation/python-sdk-docs/source/integrations/openai/track_openai.rst

@@ -0,0 +1,4 @@
+track_openai
+============
+
+.. autofunction:: opik.integrations.openai.track_openai