Stack Overflow
Stack Overflow

Questions tagged [llama-index]

112 questions
2
votes
2 answers

tenacity.RetryError: RetryError[]

I am trying to deploy an app made with streamlit (using also streamlit_chat and streamlit_authenticator). This app is making use of llama-index to create a query engine incorporating chatgpt api. When I state "streamlit run app.py" in my computer,…
Hugo Albert
  • 31
  • 1
  • 3
2
votes
1 answer

Is there a way to stream output in Fastapi from the response I get from llama-index

I have the following code where I am asking questions based on my context, and am able to get the respective outputs in streaming format. However, I am creating an api for the same and not able to replicate similar results from langchain import…
Vivek
  • 124
  • 14
2
votes
0 answers

I want to train a open source LLM model on my custom dataset [don't want to use openai]

I am trying to use a open source LLM model ggml-gpt4all-l13b-snoozy.bin (it is downloaded from https://gpt4all.io/index.html). I want to use the same model embeddings and create a ques answering chat bot for my custom data (using the lanchain and…
ankitmhjn5
  • 89
  • 5
2
votes
1 answer

Langchain - rely ONLY on the context

My goal is to make a ChatBot able to: have memory take as input some documents rely ONLY on the documents given and say "I don't know" when the information is not in the input documents. I found this tutorial, super useful:…
Carlo
  • 31
  • 3
1
vote
1 answer

Very slow Response from LLM based Q/A query engine

I built a Q/A query bot over a 4MB csv file I have in my local, I'm using chroma for vector DB creation and with embedding model being Instructor Large from hugging face, and LLM chat model being LlamaCPP=llama2-13b-chat, The Vector Database created…
Avish Wagde
  • 33
  • 4
1
vote
0 answers

LangChain and LLama index Chatbot on ingested data

I am new to the world of LangChain and LLama Index. I am working on a project for document consultation (building regulations) using LLMs. I noticed that when, for example, on LLama Index, I use the query engine, the responses are based solely on…
Marco Palombo
  • 11
  • 1
1
vote
2 answers

AttributeError: 'VectorStoreIndex' object has no attribute 'documents'

I am building my first chatbot trained on my database. I've stucked and can't move forward with the last part of my code :( My code looks as follows: import os from llama_index import SimpleDirectoryReader, GPTListIndex, GPTVectorStoreIndex,…
Renata Ka
  • 21
  • 2
1
vote
0 answers

How can I store an ObjectIndex in my file system so I don't need to recreate it every time with LlamaIndex?

Starting off by saying that I'm totally new to this, so super thankful for any help I can get! I have the following code (from one of the SQL examples from LlamaIndex's website) engine = create_engine('url') sql_database =…
Twixen
  • 11
  • 1
1
vote
1 answer

Unable to get file meta data information in Llama index

I am unable to extract metadata information from the documents. PFB my code filename_fn = lambda filename: {'file_name': filename} documents = SimpleDirectoryReader("../data", file_metadata=filename_fn).load_data() print([x for x in…
Nithin
  • 9,661
  • 14
  • 44
  • 67
1
vote
2 answers

ImportError: cannot import name 'GPTSimpleVectorIndex' from 'llama_index'

I am getting an ImportError while using GPTSimpleVectorIndex from the llama-index library. Have installed the latest version of llama-index library and trying to run it on python 3.9. from llama_index import GPTSimpleVectorIndex,…
Codemaker2015
  • 12,190
  • 6
  • 97
  • 81
1
vote
0 answers

How to optimize the building time with LlamaIndex by storing an agent or a toolkit?

I'm currently building a chatbot agent with llama_index to take benefit of a dataset of 13 000 documents I have. However, making the toolkit to then build the agent takes a lot of time (4h) because I have to load the indexes to make the actual…
Hugo Lamoureux
  • 19
  • 3
1
vote
1 answer

OpenAI Fine-tunes API: Why would I use LlamaIndex or LangChain instead of fine-tuning a model?

I'm just getting started with working with LLMs, particularly OpenAIs and other OSS models. There are a lot of guides on using LlamaIndex to create a store of all your documents and then query on them. I tried it out with a few sample documents, but…
Curunir The Colorful
  • 33
  • 5
1
vote
2 answers

Fine Tuning Llama on Unlabelled Data

I'd like to use Llama to do a conversational chat bot to answer questions on scientific news articles. Can I use a collection of unlabelled scientific articles to fine tune Llama and to "increase its vocabulary"/"extend its knowledge base"? I'm not…
Ong Hai Xiang
  • 11
  • 2
1
vote
1 answer

How to properly import llama-index classes?

Recently I making some PoCs using Llama Index. I'm following the documentation in order to use routing features for different indexes. I made two indexes and I want to use SubQueryEngine to route the query engines that I have created. In the…
Thauany Moedano
  • 551
  • 2
  • 8
  • 21
1
vote
1 answer

is there a solution to get the full response from a gpt model?

I am trying to train a gpt model using openai api and langchain in order to make a chatbot on my custom data, I have prepared my data in txt format and when the user ask a question get the response correctly but I am facing a problem which is the…
Mohamad
  • 21
  • 2
1
2
3 4 5 6 7 8