Stack Overflow
Stack Overflow

Questions tagged [langchain]

LangChain is an open-source framework for developing applications powered by language models. Use [py-langchain] for the python-specific package.

LangChain is an open-source framework for developing applications powered by language models. Use [py-langchain] for the python-specific package.

672 questions
-1
votes
0 answers

how do I make my chatGPT 3.5 turbo API integrated langchain chatbot ask a particular set of questions?

I am facing an issue where I cannot determine how to make the chatbot ask a particular set of questions from the user, then take all of that data to produce a response and store it for future reference. I am using ChatGPT 3.5-turbo API and…
Hamza Ahmed
  • 1
-1
votes
1 answer

How can I use cheerio web scraper as an agent tool in Flowise?

I am developing a small project on Flowise and I need to use Cheerio web scraper as a tool for agent. How can I do this? Or is there any way or tool to do in python langchain app when I give the website url, it scraps and give me the all text?
batuhan
  • 19
  • 1
  • 2
-1
votes
1 answer

Working with Langchain I get nlkt errors telling me: Package "tokenizers" not found in index and Packaage "taggers" not found in index

I'm trying to load some documents, powerpoints and text to train my custom LLm using Langchain. When I run it I come to a weird error message where it tells I don't have "tokenizers" and "taggers" packages (folders). I've read the docs, asked…
Zaesar
  • 352
  • 1
  • 3
  • 12
-1
votes
1 answer

LLM's answering out of context ( trained on user data)

I have trained LLM on my PDF file now I am asking questions related to same, but if a question is being asked out of the context I want the answer as " I don't know " or " out of context " Right now it is answering even out of context I have used…
Mukilan
  • 1
  • 1
-1
votes
1 answer

How can I use `langchain.document_loaders.PyPDFLoader` for pdf documents uploaded on StreamLit?

I am trying to build a webapp using StreamLit for reading documents (mainly pdf) and load the data using langchain.document_loaders.PyPDFLoader but I am ending up with an error as follows: TypeError: stat: path should be string, bytes, os.PathLike…
Shuhul Handoo
  • 122
  • 8
-1
votes
1 answer

override langchain llm completion call to handle 400 moderated response

Using langchain==0.0.198, langchainplus-sdk==0.0.8, python==3.10 I am working with openAI, Azure. Currently, the moderation endpoint that was available in the non-Azure openAI is no longer available with Azure openAI, and has been "bundled" with the…
camelBack
  • 748
  • 2
  • 11
  • 30
-1
votes
1 answer

ChromaDB API deployment does not work with Python LangChain on Windows Machine

I have installed chromaDB via pip using command: pip install chromadb LangChain integration with other libraries seem to be working fine. I get the following error:
Reeshabh Choudhary
  • 50
  • 8
-1
votes
1 answer

Invalid _type: undefined in loadQAChain in TypeScript LangChain

I am trying to use loadQAChain with a custom prompt. The code to make the chain looks like this: import { OpenAI } from 'langchain/llms/openai'; import { PineconeStore } from 'langchain/vectorstores/pinecone'; import { LLMChain, loadQAChain,…
oi-bb-2003
  • 1
  • 2
-1
votes
2 answers

Manage search results in Langchain

I am kind of new to Langchain. I wanted to create an app that uses Langchain's search agents like serpapi and find some useful information on the internet. But most of the times, when I want references from it, it returns irrelevant sources. I want…
kheirq
  • 31
  • 2
-1
votes
1 answer

Chat history in conversation buffer memory not getting stored when put in a function

I have written a simple function to get summary from my data and in that I am adding memory (chat_history) using Conversation Buffer Memory for follow up questions. When the code below is not in a function, I see chat_history gets loaded in the…
Srishino
  • 43
  • 10
-2
votes
0 answers

langchain SeleniumUrlLoader not working in AWS ec2 Ubuntu server

Message: unknown error: Chrome failed to start: exited abnormally. (unknown error: DevToolsActivePort file doesn't exist) (The process started from chrome location /home/ubuntu/.cache/selenium/chrome/linux64/116.0.5845.96/chrome is no longer…
user22403491
  • 7
  • 2
-2
votes
1 answer

Predicting next questions in llm powered chatbot

I am building a question answering chatbot powered by llms. I have seen in chatbots like bing chat it predicts what might be the top three next questions user may ask. My question is: How would I do the same in my chatbot? I have implemented the qa…
CaptainAmerica
  • 31
  • 4
-2
votes
0 answers

get the source of an answer produced by langchainai

I am currently playing around with langchainai and openAi. My goal is to make a kind of a chatbot which can answer questions specific to certain documents. It does work currently: export async function query(req: Request, res: Response) { const…
Hannes F
  • 339
  • 2
  • 11
-2
votes
1 answer

Get chatGPT to respond with a single direct answer

I am querying a text using chatGPT. But I need chatGPT to respond with single direct answers, rather than long stories or irrelevant text. Any way to achieve this? My code looks like: from langchain.document_loaders import TextLoader from…
trazoM
  • 50
  • 1
  • 8
-2
votes
2 answers

{ "message": "Error : An error occurred: 'str' object does not support item assignment." }

I have a blob storage account where I dropped a single file. Then I want to add a record on pinecone based on this file using langchain: @app.get("/BlobStorage") def IndexContainer(storageContainer: str, indexName: str, namespace_name: str): …
Luis Valencia
  • 32,619
  • 93
  • 286
  • 506
1 2 3
…
44
45