All Questions
Tagged with large-language-model chatbot
68
questions
-1
votes
0
answers
14
views
Langchain agent not using tool every time in react for pdfchat, and concludes with wrong answer
Im using the react template proposed by langchain hwchase17/react-chat react template with chat history. when using this template sometimes it fails to look into rag tool so it is getting results from ...
-1
votes
0
answers
30
views
Embedding and Vector Search with Milvus
I am trying to make a RAG-based chatbot application that lets the user prompt in natural language and receive relevant information that can be retrieved a collection of from multiple tables, all of ...
0
votes
0
answers
36
views
multiple headers excel loader,langchain , excel chatbot
i am creating question and answer using excel, i am using recursive text splitter.i am able to generate answer for simple excel files but the problem is with the excel file with multiple headers
like](...
1
vote
0
answers
32
views
Fine-tuned LLaMA-2-Chat-HF Model Generates Same Responses as Pre-trained Model and Suitability for Retrieval-based Task
I am working on building a chatbot for substance abuse support. My approach involves two main steps:
Fine-tuning the LLaMA-2-Chat-HF model: I have fine-tuned the LLaMA-2-Chat-HF model using a dataset ...
0
votes
0
answers
25
views
How do you handle different types of responses in your chatbot with Spring AI?
How can we design a Spring AI chatbot to handle different types of responses in the same endpoint, without resorting to multiple if-else statements in the controller? What strategies, design patterns, ...
0
votes
0
answers
111
views
How to Parallelize Responses to Multiple User Queries in Langchain
I am currently developing a chatbot using Langchain, and I load the model using LlamaCPP. The responses are generated through a chain process. However, I encounter an issue where the process crashes ...
0
votes
1
answer
256
views
Chainlit Stream responses from Groq & Langchain
my Chainlit AI chat application uses Groq, OpenAI embeddings, LangChain and Chromadb, and it allows the user to upload a PDF and interact with it. It works fine, but it spits out the whole response.
I'...
0
votes
1
answer
647
views
Azure OpenAI error Error code: 400 - {'statusCode': 400, 'message': "Unable to parse and estimate tokens from incoming request
I used this API a lot in the last few days, and today it's not working, and I don't know what's wrong:
prompt = """some complex prompt (just text
"""
response = client....
0
votes
0
answers
243
views
using RunnablePassthrough() on promt template LangChain JS
I've been learning couple weeks how to use Langchain and I started to follow the tutorial that they show on their website https://js.langchain.com/v0.1/docs/expression_language/cookbook/retrieval/
and ...
0
votes
0
answers
44
views
TypeError: string indices must be integers when using FAISS for context in a chatbot
Question:
I'm building a chatbot that incorporates a conversational retrieval system using Transformers and Gradio. The system retrieves context using FAISS for query context. However, I'm ...
-2
votes
1
answer
89
views
Visualizing SQL Data using Generative AI
I am seeking a solution for data visualization using Generative AI that works on databases containing multiple tables. While I have found solutions like PandasAI and LIDA that work with a single CSV ...
0
votes
0
answers
51
views
Paraphrasing the response from LLM as per our need
I am trying to understand few things here. Here is my requirement.
I give a prompt and for this prompt the I have an agent that should call 3 plugins. Since there were some inconsistencies in the ...
0
votes
1
answer
95
views
Pinecone serverless from existing index
from flask import Flask, render_template, jsonify, request
from src.helper import download_hugging_face_embeddings
# from langchain.vectorstores import Pinecone
import pinecone
from langchain.prompts ...
0
votes
1
answer
69
views
langchaine gemini rag based chatbot hallucinating by combining info from differents documents
So im creating a chatbot for my university website using langchain and gemini LLM.
the problem is when asked some questions the answer is a combinations of the documents retrieved from the RAG and ...
0
votes
0
answers
63
views
Is there is any information available on how llama index calculates a score for its correctness evaluator?
I have been developing a chatbot which uses llama-2 and llama index to build the knowledge base and was planning on using the llama index evaluators to test how good it is. The problem is, I am ...