feat(haystack): Added Components instrumentation

python/instrumentation/openinference-instrumentation-haystack/examples/agent_run.py

@@ -0,0 +1,48 @@
+from haystack.components.agents import Agent
+from haystack.components.generators.chat import OpenAIChatGenerator
+from haystack.dataclasses import ChatMessage
+from haystack.tools import Tool
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
+from opentelemetry.sdk import trace as trace_sdk
+from opentelemetry.sdk.trace.export import SimpleSpanProcessor
+
+from openinference.instrumentation.haystack import HaystackInstrumentor
+
+# Configure HaystackInstrumentor with Phoenix endpoint
+endpoint = "http://127.0.0.1:6006/v1/traces"
+tracer_provider = trace_sdk.TracerProvider()
+tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
+
+HaystackInstrumentor().instrument(tracer_provider=tracer_provider)
+
+
+def search_documents(query: str, user_context: str) -> dict:
+    """Search documents using query and user context."""
+    return {"results": [f"Found results for '{query}' (user: {user_context})"]}
+
+
+# Create tool that reads from state
+search_tool = Tool(
+    name="search",
+    description="Search documents",
+    parameters={
+        "type": "object",
+        "properties": {"query": {"type": "string"}, "user_context": {"type": "string"}},
+        "required": ["query"],
+    },
+    function=search_documents,
+    inputs_from_state={"user_name": "user_context"},
+    # Maps state's "user_name" to the tool’s input parameter “user_context”
+)
+
+# Define agent with state schema including user_name
+agent = Agent(
+    chat_generator=OpenAIChatGenerator(),
+    tools=[search_tool],
+    state_schema={"user_name": {"type": str}, "search_results": {"type": list}},
+)
+
+# Initialize agent with user context
+result = agent.run(
+    messages=[ChatMessage.from_user("Search for Python tutorials")], user_name="Alice"
+)

python/instrumentation/openinference-instrumentation-haystack/examples/agent_with_pipeline.py

@@ -0,0 +1,72 @@
+from typing import Optional
+
+from haystack.components.agents import Agent
+from haystack.components.builders.chat_prompt_builder import ChatPromptBuilder
+from haystack.components.converters.html import HTMLToDocument
+from haystack.components.fetchers.link_content import LinkContentFetcher
+from haystack.components.generators.chat import OpenAIChatGenerator
+from haystack.core.pipeline import Pipeline
+from haystack.dataclasses import ChatMessage, Document
+from haystack.document_stores.in_memory import InMemoryDocumentStore
+from haystack.tools import tool
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
+from opentelemetry.sdk import trace as trace_sdk
+from opentelemetry.sdk.trace.export import SimpleSpanProcessor
+
+from openinference.instrumentation.haystack import HaystackInstrumentor
+
+endpoint = "http://127.0.0.1:6006/v1/traces"
+tracer_provider = trace_sdk.TracerProvider()
+tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
+
+HaystackInstrumentor().instrument(tracer_provider=tracer_provider)
+
+document_store = InMemoryDocumentStore()  # create a document store or an SQL database
+
+
+@tool
+def add_database_tool(name: str, surname: str, job_title: Optional[str], other: Optional[str]):
+    """Use this tool to add names to the database with information about them"""
+    document_store.write_documents(
+        [Document(content=name + " " + surname + " " + (job_title or ""), meta={"other": other})]
+    )
+    return
+
+
+database_assistant = Agent(
+    chat_generator=OpenAIChatGenerator(model="gpt-4o-mini"),
+    tools=[add_database_tool],
+    system_prompt="You are a database assistant. Extract all people’s names and relevant details"
+    " from the given context (using only the provided text), add them to the "
+    "knowledge base automatically, and return a brief summary of the added entries.",
+    exit_conditions=["text"],
+    max_agent_steps=100,
+    raise_on_tool_invocation_failure=False,
+)
+
+builder = ChatPromptBuilder(
+    template=[
+        ChatMessage.from_user("""
+    {% for doc in docs %}
+    {{ doc.content|default|truncate(25000) }}
+    {% endfor %}
+    """)
+    ],
+    required_variables=["docs"],
+)
+
+extraction_agent = Pipeline()
+extraction_agent.add_component("fetcher", LinkContentFetcher())
+extraction_agent.add_component("converter", HTMLToDocument())
+extraction_agent.add_component("builder", builder)
+
+extraction_agent.add_component("database_agent", database_assistant)
+extraction_agent.connect("fetcher.streams", "converter.sources")
+extraction_agent.connect("converter.documents", "builder.docs")
+extraction_agent.connect("builder", "database_agent")
+
+agent_output = extraction_agent.run(
+    {"fetcher": {"urls": ["https://en.wikipedia.org/wiki/Deepset"]}}
+)
+
+print(agent_output["database_agent"]["messages"][-1].text)

python/instrumentation/openinference-instrumentation-haystack/examples/retriever_component_run.py

@@ -0,0 +1,44 @@
+import asyncio
+
+from haystack import Document
+from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
+from haystack.document_stores.in_memory import InMemoryDocumentStore
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
+from opentelemetry.sdk import trace as trace_sdk
+from opentelemetry.sdk.trace.export import SimpleSpanProcessor
+
+from openinference.instrumentation.haystack import HaystackInstrumentor
+
+endpoint = "http://127.0.0.1:6006/v1/traces"
+tracer_provider = trace_sdk.TracerProvider()
+tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
+
+HaystackInstrumentor().instrument(tracer_provider=tracer_provider)
+
+document_store = InMemoryDocumentStore()
+documents = [
+    Document(content="There are over 7,000 languages spoken around the world today."),
+    Document(
+        content="Elephants have been observed to behave in a way that indicates "
+        "a high level of self-awareness, such as recognizing themselves "
+        "in mirrors."
+    ),
+    Document(
+        content="In certain parts of the world, like the Maldives, Puerto Rico, "
+        "and San Diego, you can witness the phenomenon of bioluminescent "
+        "waves."
+    ),
+]
+document_store.write_documents(documents=documents)
+
+
+async def run():
+    retriever = InMemoryBM25Retriever(document_store=document_store)
+    result = await retriever.run_async(
+        query="How many languages are spoken around the world today?"
+    )
+    print(result)
+
+
+if __name__ == "__main__":
+    asyncio.run(run())

python/instrumentation/openinference-instrumentation-haystack/src/openinference/instrumentation/haystack/__init__.py

@@ -137,6 +137,14 @@ def wrap_component_run_method(
                 tracer=self._tracer, wrap_component_run_method=wrap_component_run_method
             ),
         )
+        from haystack.core.component.component import component
+
+        for class_path, cls in component.registry.items():
+            # Ensure the class looks like a Component (has run or run_async)
+            if hasattr(cls, "run"):
+                wrap_component_run_method(cls, cls.run)
+            if hasattr(cls, "run_async"):
+                wrap_component_run_method(cls, cls.run_async)
 
     def _uninstrument(self, **kwargs: Any) -> None:
         import haystack

python/instrumentation/openinference-instrumentation-haystack/src/openinference/instrumentation/haystack/_wrappers.py

@@ -134,7 +134,7 @@ def __call__(
         bound_arguments = _get_bound_arguments(wrapped, *args, **kwargs)
 
         with self._tracer.start_as_current_span(
-            name=_get_component_span_name(component_class_name)
+            name=_get_component_span_name(component_class_name, wrapped)
         ) as span:
             component_type = _get_component_type(component)
             span.set_attributes(_set_component_runner_request_attributes(bound_arguments, instance))
@@ -170,7 +170,7 @@ async def __call__(
         bound_arguments = _get_bound_arguments(wrapped, *args, **kwargs)
         component_type = _get_component_type(instance)
         with self._tracer.start_as_current_span(
-            name=_get_component_span_name(component_class_name),
+            name=_get_component_span_name(component_class_name, wrapped),
             attributes=_set_component_runner_request_attributes(bound_arguments, instance),
         ) as span:
             result = await wrapped(*args, **kwargs)
@@ -325,11 +325,11 @@ def _get_component_class_name(component: "Component") -> str:
     return str(component.__class__.__name__)
 
 
-def _get_component_span_name(component_class_name: str) -> str:
+def _get_component_span_name(component_class_name: str, wrapped: Callable[..., Any]) -> str:
     """
     Gets the name of the span for a component.
     """
-    return f"{component_class_name}.run"
+    return f"{component_class_name}.{wrapped.__name__}"
 
 
 def _get_component_type(component: "Component") -> ComponentType:

python/instrumentation/openinference-instrumentation-haystack/tests/openinference/haystack/cassettes/test_instrumentor/test_agent_run_component_spans[False].yaml

@@ -0,0 +1,55 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"user","content":"Search for Python tutorials"}],"model":"gpt-4o-mini","n":1,"stream":false,"tools":[{"type":"function","function":{"name":"search","description":"Search
+      documents","parameters":{"type":"object","properties":{"query":{"type":"string"},"user_context":{"type":"string"}},"required":["query"]}}}]}'
+    headers: {}
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-CWletHyGzapkvp0MG02ee7Jwn1x7B\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1761925731,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_BjOwGgWvcqqtxtVBYWjhPRfu\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"search\",\n
+        \             \"arguments\": \"{\\\"query\\\":\\\"Python tutorials\\\"}\"\n
+        \           }\n          }\n        ],\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 48,\n    \"completion_tokens\":
+        14,\n    \"total_tokens\": 62,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_51db84afab\"\n}\n"
+    headers: {}
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"user","content":"Search for Python tutorials"},{"role":"assistant","tool_calls":[{"type":"function","function":{"name":"search","arguments":"{\"query\":
+      \"Python tutorials\"}"},"id":"call_BjOwGgWvcqqtxtVBYWjhPRfu"}]},{"role":"tool","content":"{''results'':
+      [\"Found results for ''Python tutorials'' (user: Alice)\"]}","tool_call_id":"call_BjOwGgWvcqqtxtVBYWjhPRfu"}],"model":"gpt-4o-mini","n":1,"stream":false,"tools":[{"type":"function","function":{"name":"search","description":"Search
+      documents","parameters":{"type":"object","properties":{"query":{"type":"string"},"user_context":{"type":"string"}},"required":["query"]}}}]}'
+    headers: {}
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-CWleuO1zD8b4RnjEM1j1FOmAKwpQy\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1761925732,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"I found some results for \\\"Python
+        tutorials.\\\" Would you like more specific information about them?\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        87,\n    \"completion_tokens\": 19,\n    \"total_tokens\": 106,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_51db84afab\"\n}\n"
+    headers: {}
+    status:
+      code: 200
+      message: OK
+version: 1

python/instrumentation/openinference-instrumentation-haystack/tests/openinference/haystack/cassettes/test_instrumentor/test_agent_run_component_spans[True].yaml

@@ -0,0 +1,55 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"user","content":"Search for Python tutorials"}],"model":"gpt-4o-mini","n":1,"stream":false,"tools":[{"type":"function","function":{"name":"search","description":"Search
+      documents","parameters":{"type":"object","properties":{"query":{"type":"string"},"user_context":{"type":"string"}},"required":["query"]}}}]}'
+    headers: {}
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-CWletHyGzapkvp0MG02ee7Jwn1x7B\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1761925731,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_BjOwGgWvcqqtxtVBYWjhPRfu\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"search\",\n
+        \             \"arguments\": \"{\\\"query\\\":\\\"Python tutorials\\\"}\"\n
+        \           }\n          }\n        ],\n        \"refusal\": null,\n        \"annotations\":
+        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"tool_calls\"\n
+        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 48,\n    \"completion_tokens\":
+        14,\n    \"total_tokens\": 62,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_51db84afab\"\n}\n"
+    headers: {}
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"user","content":"Search for Python tutorials"},{"role":"assistant","tool_calls":[{"type":"function","function":{"name":"search","arguments":"{\"query\":
+      \"Python tutorials\"}"},"id":"call_BjOwGgWvcqqtxtVBYWjhPRfu"}]},{"role":"tool","content":"{''results'':
+      [\"Found results for ''Python tutorials'' (user: Alice)\"]}","tool_call_id":"call_BjOwGgWvcqqtxtVBYWjhPRfu"}],"model":"gpt-4o-mini","n":1,"stream":false,"tools":[{"type":"function","function":{"name":"search","description":"Search
+      documents","parameters":{"type":"object","properties":{"query":{"type":"string"},"user_context":{"type":"string"}},"required":["query"]}}}]}'
+    headers: {}
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"id\": \"chatcmpl-CWleuO1zD8b4RnjEM1j1FOmAKwpQy\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1761925732,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"I found some results for \\\"Python
+        tutorials.\\\" Would you like more specific information about them?\",\n        \"refusal\":
+        null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n
+        \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        87,\n    \"completion_tokens\": 19,\n    \"total_tokens\": 106,\n    \"prompt_tokens_details\":
+        {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_51db84afab\"\n}\n"
+    headers: {}
+    status:
+      code: 200
+      message: OK
+version: 1