Stack Overflow
Stack Overflow

Questions tagged [llama-index]

112 questions
0
votes
1 answer

Llama-index how to execute search query against OpenSearch Elasticsearch index?

I have this code where I am able to create an index in Opensearch Elasticsearch: def openes_initiate(file): endpoint = getenv("OPENSEARCH_ENDPOINT", "http://localhost:9200") # index to demonstrate the VectorStore impl idx =…
user2966197
  • 2,793
  • 10
  • 45
  • 77
0
votes
0 answers

OSError: integer divide by zero for using llama_index with local Vicuna and embedder

I'm currently trying to implement a simple information retrival with llama_index and locally running both the emdedder and llm model. But whenever I execute the following code I get a OSError: exception: integer divide by zero. This is my…
Jan-Ole K.
  • 11
  • 1
0
votes
0 answers

Fixing error in GPTVectorStoreIndex - ValueError: One of documents or index_struct must be provided

I want to train LLM on custom dataset. This is my code: from llama_index import SimpleDirectoryReader, GPTListIndex, GPTVectorStoreIndex, LLMPredictor, PromptHelper from langchain import OpenAI import os apikey =…
taga
  • 3,537
  • 13
  • 53
  • 119
0
votes
1 answer

How to support OpenAI's Chat Completions API format in LlamaIndex?

I'm currently using LlamaIndex for a project, and I'm trying to find a way to support the complex prompt format used by OpenAI's Chat Completions API within the chat engine of LlamaIndex. The OpenAI API uses a list of messages for its prompts, where…
Ray
  • 1
0
votes
0 answers

How to save each user's index from Llama index to PostgreSQL database in chatGPT clone app

I am trying to make a chatGPT clone that can answer on external data (private data) using React, Django, OpenAI API, PostgreSQL, and Llama index, precisely speaking, in context learning. Then, my question is, how can I save each user's data (= index…
user21938333
0
votes
0 answers

Using Pandas to create a Q&A chatbot in LLamaIndex

Currently I have a Database with Questions on column A and answers on column B. I Want to create a chatbot that takes the user’s question, searches the most similar question on Column A and outputs its correspondent answer from column B. I tried…
Cristian Quitian
  • 1
0
votes
1 answer

How does Llamaindex elasticsearch vector work

I am building an app to use Opensearch as vecotr store with Llamaindex using this example. Here is the code I have: endpoint = getenv("OPENSEARCH_ENDPOINT", "http://localhost:9200") idx = getenv("OPENSEARCH_INDEX", "gpt-index-demo") …
user2966197
  • 2,793
  • 10
  • 45
  • 77
0
votes
1 answer

Failing to install llama-index package

can you please help me with this issue (llama-index installation fails. I have the latest version of pip and almost tried everything but still getting the same error when the llama-index installation reaches this point. I am not that experienced and…
davoud malekian
  • 5
  • 3
0
votes
0 answers

Llamaindex SIGILL on Mac M1

I am trying to replicate the Llamaindex demo (here: https://colab.research.google.com/drive/16QMQePkONNlDpgiltOi7oRQgmB8dU5fl?usp=sharing#scrollTo=20cf0152) on my Mac M1 but I keep hitting this error: Process finished with exit code 132 (interrupted…
Tom_Scott
  • 95
  • 7
0
votes
1 answer

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

I met the error when I tried to run the sample code in the git of Llamaindex 0.6.5. How can I import 'load_index_from_storage' properly? or is there any alternative? Language: python. IDE: VScode. from llama_index import GPTVectorStoreIndex, …
David Seo
  • 1
  • 1
  • 2
0
votes
0 answers

Issues installing Vicuna 13B

I've been using the installation guide https://github.com/vicuna-tools/vicuna-installation-guide and BING assistant to try get me through installing Vicuna 13B on my Ubuntu PC, but seem to be banging my head against errors. I now believe I have what…
Alonso Ibata
  • 11
0
votes
2 answers

Longer Responses with LlamaIndex?

I currently have LlamaIndex functioning off some private data just fine, however, it only outputs about 1000 characters worth. How do I extend the output until its completion? I know I can bump the tokens a bit, but I'm looking at potentially pages…
Jon
  • 573
  • 1
  • 6
  • 12
0
votes
1 answer

Data Protection when indexing and querying your own documents using LlamaIndex and LangChain

we have some sensitive data which we want to Data Ingestion, Data Indexing locally on prem but should not be sent externally from the company network In this case such as langchain.vectorstores stores locally for Data Ingestion, Data Indexing what…
Jeff Power
  • 33
  • 6
0
votes
2 answers

I'm trying to run the llama index model, but when I get to the index building step - it fails time and time again, how can I fix this?

I'm trying to use the llama_index model which builds an index from your personal documents, and allows you to ask questions about the information from the GPT chat. This is the full code (of course with my API): import…
NH.LOCAL
  • 21
  • 7
0
votes
0 answers

How can I put a python program with specific module dependencies into an HTML page?

I am trying to make a modified GPT model, designed with Python, available for questions on an HTML page. I have tried using PyScript but I do not know how to give it access to the modules that I want. Here is my python code in the file gpt.py: from…
Nico Rose
  • 13
  • 4
1 2 3 4 5 6
7
8