[FEATURE]: LangChain Traceability

[zycarlc]

Feature summary

Get user to trace their LLM usage on LangChain

Feature description

Since this project uses LangChain to manage all the LLM requests, It would be great to let user to trace all the use of LLM on LangChain/LangSmith platform.

I tried to supply the LangChain environment variables in the main func as instructed by LangChain:

    `os.environ['LANGCHAIN_TRACING_V2'] = 'true'
    os.environ['LANGCHAIN_ENDPOINT']="https://api.smith.langchain.com"
    os.environ['LANGCHAIN_API_KEY']="******************"
    os.environ['LANGCHAIN_PROJECT']="*******"`

error:

Failed to batch ingest runs: LangSmithError('Failed to POST https://api.smith.langchain.com/runs/batch in LangSmith API. HTTPError(\'403 Client Error: Forbidden for url: https://api.smith.langchain.com/runs/batch\', \'{"detail":"Forbidden"}\')') ^C Aborted! Failed to batch ingest runs: LangSmithError('Failed to POST https://api.smith.langchain.com/runs/batch in LangSmith API. HTTPError(\'403 Client Error: Forbidden for url: https://api.smith.langchain.com/runs/batch\', \'{"detail":"Forbidden"}\')')

Motivation

No response

Alternatives considered

No response

Additional context

No response

[feder-cr]

@zycarlc Hi, do you want to work on this?

For better communication with other open source developers I suggest you join our discord group: https://discord.gg/mMZcMTH9K6