ERROR:openinference.instrumentation.langchain._tracer:Failed to get attribute

[cmosguy]

I am doing simple langchain and langgraph stuff.

import phoenix as px
from phoenix.trace.langchain import LangChainInstrumentor
px.launch_app()
LangChainInstrumentor().instrument()

run my workflow here

When I run the my langgraph workflow, I see:

ERROR:openinference.instrumentation.langchain._tracer:Failed to get attribute.
Traceback (most recent call last):
  File "/opt/miniconda3/envs/proj/lib/python3.10/site-packages/openinference/instrumentation/langchain/_tracer.py", line 236, in wrapper
    yield from wrapped(*args, **kwargs)
  File "/opt/miniconda3/envs/proj/lib/python3.10/site-packages/openinference/instrumentation/langchain/_tracer.py", line 325, in _input_messages
    assert hasattr(message_data, "get"), f"expected Mapping, found {type(message_data)}"
AssertionError: expected Mapping, found <class 'tuple'>
ERROR:openinference.instrumentation.langchain._tracer:Failed to get attribute.
Traceback (most recent call last):
  File "/opt/miniconda3/envs/proj/lib/python3.10/site-packages/openinference/instrumentation/langchain/_tracer.py", line 236, in wrapper
    yield from wrapped(*args, **kwargs)
  File "/opt/miniconda3/envs/proj/lib/python3.10/site-packages/openinference/instrumentation/langchain/_tracer.py", line 325, in _input_messages
    assert hasattr(message_data, "get"), f"expected Mapping, found {type(message_data)}"
AssertionError: expected Mapping, found <class 'tuple'>

I am using versions:

arize-phoenix==3.23.0
openinference-instrumentation==0.1.1
openinference-instrumentation-langchain==0.1.14
openinference-instrumentation-llama-index==1.2.1
openinference-instrumentation-openai==0.1.4
openinference-semantic-conventions==0.1.5
opentelemetry-api==1.24.0
opentelemetry-exporter-otlp==1.24.0
opentelemetry-exporter-otlp-proto-common==1.24.0
opentelemetry-exporter-otlp-proto-grpc==1.24.0
opentelemetry-exporter-otlp-proto-http==1.24.0
opentelemetry-instrumentation==0.45b0
opentelemetry-instrumentation-asgi==0.45b0
opentelemetry-instrumentation-fastapi==0.45b0
opentelemetry-proto==1.24.0
opentelemetry-sdk==1.24.0
opentelemetry-semantic-conventions==0.45b0
opentelemetry-util-http==0.45b0
langchain==0.1.16
langchain-community==0.0.33
langchain-core==0.1.48
langchain-openai==0.1.4
langchain-text-splitters==0.0.1
langchainhub==0.1.15
openinference-instrumentation-langchain==0.1.14

[dosubot[bot]]

The error "AssertionError: expected Mapping, found <class 'tuple'>" indicates that a tuple is being passed where a mapping (like a dictionary) is expected, specifically in the openinference/instrumentation/langchain/_tracer.py file. This issue likely arises from how data is being passed or expected within your workflow, particularly in relation to the LangChainInstrumentor or the OpenTelemetry configuration.

To address this, ensure that all interactions with the LangChainInstrumentor and any related OpenTelemetry configurations are correctly handling data types, especially where mappings are expected instead of tuples. Review any custom code or overrides that might be altering the expected data types or structures being passed to these components.

If the problem continues, providing more details about how you're using the LangChainInstrumentor in your workflow, including any custom configurations or interactions with OpenTelemetry components, would be helpful for further diagnosis.

Details

Sources

• src/phoenix/trace/langchain/instrumentor.py
• CHANGELOG.md

About Dosu This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

[axiomofjoy]

Thanks for reporting @cmosguy. Can you send a snippet of the LangChain code to reproduce?

[axiomofjoy]

@cmosguy I am not able to reproduce the issue on the notebook link you sent. I am able to get traces from this notebook into Phoenix. Here's a link to a slightly modified version that is working for me. https://colab.research.google.com/drive/1xDEPe2i_2rRqs7o6oNTtqA4J7Orsnvx1?usp=sharing

Here are some relevant requirements.

arize-phoenix==4.0.0
langchain==0.1.19
langchain-core==0.1.52
langchain-experimental==0.0.58
langchain-openai==0.1.6
langgraph==0.0.48
openai==1.27.0
openinference-instrumentation==0.1.5
openinference-instrumentation-langchain==0.1.14
openinference-instrumentation-openai==0.1.4
opentelemetry-api==1.24.0
opentelemetry-exporter-otlp==1.24.0
opentelemetry-exporter-otlp-proto-common==1.24.0
opentelemetry-exporter-otlp-proto-grpc==1.24.0
opentelemetry-exporter-otlp-proto-http==1.24.0
opentelemetry-instrumentation==0.45b0
opentelemetry-proto==1.24.0
opentelemetry-sdk==1.24.0
opentelemetry-semantic-conventions==0.45b0

[mikeldking]

bumping priority