I am building a chatbot, following the Conversational RAG example in langchain’s documentation: https://python.langchain.com/v0.2/docs/tutorials/qa_chat_history/

I’ve started working with Langchain to get a feel of it and a lot of the videos seem outdated. After some research I learned about LCEL being used as the other methods seem to be deprecated.

I’ve started working with Langchain to get a feel of it and a lot of the videos seem outdated. After some research I learned about LCEL being used as the other methods seem to be deprecated.

I’ve started working with Langchain to get a feel of it and a lot of the videos seem outdated. After some research I learned about LCEL being used as the other methods seem to be deprecated.

I’ve started working with Langchain to get a feel of it and a lot of the videos seem outdated. After some research I learned about LCEL being used as the other methods seem to be deprecated. In my code I’m trying to use the output of one chain as the input for another but it doesn’t seem to work.

retriver = PineconeVectorStore( pinecone_api_key=pc_key, index=”index-1″, embedding=OpenAIEmbeddings() ).as_retriever() qa_chain = ( { “context”: retriver, “question”: RunnablePassthrough(), } | review_template | model | StrOutputParser() ) res =qa_chain.invoke(“Question”) print(res) Output of the code snipet : “AttributeError: ‘str’ object has no attribute ‘query” Expecting Output: retrive data from pinecone vectordb and create good answer for users. python langchain py-langchain

I am using langchain for one of my applications. Here the client sends a query regarding a search criteria. In the app the search criteria gets decomposed into multiple sub search criteria which will be mapped to different search criteria objetcs.

https://python.langchain.com/v0.2/docs/how_to/recursive_text_splitter/

I’m working with LangChain to generate responses based on user inputs. My initial prompt requires some variables, and I use these variables to generate a response. The problem arises when I try to ask a follow-up question based on the initial response; the model throws errors because it expects the initial variables again.

My goal is to limit the last N messages in a message history so I don’t overload the LLM. My plan is to use use RunnableWithMessageHistory in conjunction with a filter function. Unfortunately I seem to have two problems: 1) getting the limiting function to work; and 2) passing the actual user message into the model.