Invoking RunnableWithMessageHistory from Langserve Remote Runnable

[ashish-kumar-hpe]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

On client side I am trying to invoke RunnableWithMessageHistory as below...

Client Code
===========
llm = RemoteRunnable("http://localhost:90001/conversational_ai_with_rag_text_chat/")
config = {"configurable": {"session_id": "abc123"}}
result=llm.invoke({"question": message, "session_id": "abc123"}, config)

Server Side Code
================
original_chain = (
        {"context": reranking_retriever, "question": RunnablePassthrough()}
        | prompt_template
        | llm
        | StrOutputParser()
    )
    print("44444444444444")

    chain_with_history = RunnableWithMessageHistory(
       original_chain ,
       get_session_history,
       input_messages_key="question",
       history_messages_key="history",
    )

Error received from server
=========================
Exception: [500] Internal Server Error
{'_content': b'Internal Server Error', '_content_consumed': True, '_next': None, 'status_code': 500, 'headers': {'content-length': '21', 'content-type': 'text/plain; charset=utf-8', 'date': 'Fri, 16 May 2025 10:15:39 GMT', 'server': 'istio-envoy', 'x-envoy-upstream-service-time': '29'}, 'raw': <urllib3.response.HTTPResponse object at 0x7f81f817e710>, 'url': 'https://pcai-embedding-deployment-1-predictor-admin-6c8b1978.aie.hpelab.local/v1/embeddings', 'encoding': 'utf-8', 'history': [], 'reason': 'Internal Server Error', 'cookies': <RequestsCookieJar[]>, 'elapsed': datetime.timedelta(microseconds=35715), 'request': <PreparedRequest [POST]>, 'connection': <requests.adapters.HTTPAdapter object at 0x7f81f817f3d0>}

Description

On client side I am trying to invoke RunnableWithMessageHistory as below...

Client Code

from langserve import RemoteRunnable

llm = RemoteRunnable("http://localhost:90001/conversational_ai_with_rag_text_chat/")
config = {"configurable": {"session_id": "abc123"}}
result=llm.invoke({"question": message, "session_id": "abc123"}, config)

Server Side Code

original_chain = (
{"context": reranking_retriever, "question": RunnablePassthrough()}
| prompt_template
| llm
| StrOutputParser()
)
print("44444444444444")

chain_with_history = RunnableWithMessageHistory(
   original_chain ,
   get_session_history,
   input_messages_key="question",
   history_messages_key="history",
)

Error received from server

Exception: [500] Internal Server Error
{'_content': b'Internal Server Error', '_content_consumed': True, '_next': None, 'status_code': 500, 'headers': {'content-length': '21', 'content-type': 'text/plain; charset=utf-8', 'date': 'Fri, 16 May 2025 10:15:39 GMT', 'server': 'istio-envoy', 'x-envoy-upstream-service-time': '29'}, 'raw': <urllib3.response.HTTPResponse object at 0x7f81f817e710>, 'url': 'https://pcai-embedding-deployment-1-predictor-admin-6c8b1978.aie.hpelab.local/v1/embeddings', 'encoding': 'utf-8', 'history': [], 'reason': 'Internal Server Error', 'cookies': <RequestsCookieJar[]>, 'elapsed': datetime.timedelta(microseconds=35715), 'request': <PreparedRequest [POST]>, 'connection': <requests.adapters.HTTPAdapter object at 0x7f81f817f3d0>}

System Info

(venv310) [ashish@ai-gwrk1 chatbot]$ pip freeze|grep langchain
langchain==0.1.11
langchain-community==0.0.25
langchain-core==0.1.52
langchain-nvidia-ai-endpoints==0.1.4
langchain-text-splitters==0.0.2
langchain-weaviate==0.0.4

[ashish-kumar-hpe]

Main issue is highlighted here. #31259