LangChain "ChatOpenAI" LLM exceeding token length when using...

reno_queen

I am using Langchain to build a simple application that answers questions based on a provided document. I have implemented the following which works perfectly as a proof of concept: from langchain_openai import ChatOpenAI from langchain.vectorstores.chroma import Chroma from langchain_openai import OpenAIEmbeddings from langchain.chains import RetrievalQA embedding_client = OpenAIEmbeddings(openai_api_key) embeddings =...

Originally asked by Topazoo on Stack Exchange (stackoverflow) (CC BY-SA 4.0).

uphilltech

Good thread on this — worth a read before you pay anyone to build it.

Discussion: https://stackoverflow.com/questions/78057968/langchain-chatopenai-llm-exceeding-token-length-when-using-retrievalqa-to-answ.

Want it set up for you? UphillTech.