Questions tagged [llama-index]

112 questions
0
votes
1 answer

Do nodes in List Index come with embedding vectors in LlamaIndex?

One can run an embedding-based query on List Index (link). For that nodes in the List Index should be supplied with embedding vectors. What is then the difference between the List Index and the Vector Store Index? I thought that the distinctive…
Roman
  • 124,451
  • 167
  • 349
  • 456
0
votes
0 answers

How to pass a prompt template to GPT Index Method

I am trying to connect huggingface model with external data using GPTListIndex. GPTListIndex(documents,llm_predictor=llm_predictor) I want to use a prompt also. Here is prompt template. example_prompt = PromptTemplate( input_variables=["Query",…
Talha Anwar
  • 2,699
  • 4
  • 23
  • 62
-1
votes
1 answer

ChatGPT API Custom-trained AI Chatbot answering "None" to Python Query

I'm connecting to my first chatbot. Based on the process outlined here: https://beebom.com/how-train-ai-chatbot-custom-knowledge-base-chatgpt-api/ I created the code he suggested to get ChatGPT to analyze my PDF. The code was a bit outdated though,…
Geoff L
  • 765
  • 5
  • 22
-1
votes
1 answer

how can I import llama in python

I tried to install llama with pip: pip install llama But I got: Collecting llama Using cached llama-0.1.1.tar.gz (387 kB) Installing build dependencies ... done Getting requirements to build wheel ... error error:…
w s
  • 11
-1
votes
1 answer

How to fix `transformers` package not found error in a Python project with `py-langchain`, `llama-index`, and `gradio`?

I get this error ModuleNotFoundError: No module named 'transformers' even though I did the pip install transformers command. Could you kindly help me? Thank you My code: import os import sys from dotenv import load_dotenv import gradio as gr from…
-2
votes
0 answers

Cannot install llamacpp module provided by langchain

n_gpu_layers = 32 # Change this value based on your model and your GPU VRAM pool. n_batch = 256 # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU. # Loading model, llm = LlamaCpp( …
1 2 3 4 5 6 7
8