Questions tagged [large-language-model]
A general tag for large language model (LLM)-related subjects. Please ALWAYS use the more specific tags if available (GPT variants, PaLM , LLaMa, BLOOM, Claude etc..)
large-language-model
1,166
questions with no upvoted or accepted answers
7
votes
1
answer
823
views
How to you add context to be passed along with agent.run in ReAct LangChain framework
I've previously built a pdf searching tool in LangChain which uses the
chain.run(input_documents=, question=) syntax to ask the model questions along with context from that pdf.
I want to integrate ...
7
votes
0
answers
1k
views
Langchain - Can't solve the dynamic filtering problem from vectorstore
I am using Langchain version 0.218, and was wondering if anyone was able to filter a seeded vectorstore dynamically during runtime? Such as when running by a Agent.
My motive is to put this dynamic ...
6
votes
0
answers
2k
views
Query bot on multiple JSON files on Langchain
I have around 30 GB of JSON data with multiple files, wanted build query bot on this.
I have built same with text file but i am not sure how it will work for JSON data.
I have explored JSONLoader but ...
6
votes
1
answer
2k
views
How to finetune an LLM model on your own codebase?
I have 10 code repositories in Javascript (VueJS) (Each repository corresponds to 1 Theme)
I want to train an LLM model on these 10 code repositories so that I can generate new themes using prompts.
...
5
votes
0
answers
3k
views
Ollama - How to inject context or get model to answer based on context?
I'm trying a simple demo where I give the LLM a document and ask it to answer a few things from the document. So far I've had very little success.
My prompt is various versions of the following:
You ...
5
votes
0
answers
1k
views
What LLM have large output token limit?
We understand that OpenAI models are limited in their token output capacity. For instance, with latest gpt-4-turbo, if we input a query of about 10,000 tokens, the output generated cannot exceed 4,095 ...
5
votes
0
answers
259
views
How to protect your github code against being used for llm training
The recent rise of LLMs trained on vast amounts of data, including OS repositories, leads to a licensing question.
Suppose you are OK for other human developers to build on your code but do not want ...
4
votes
0
answers
682
views
How to load precomputed embeddings to FAISS from langchain
I am trying to read precomputed embeddings(i.e. simple vectors) into a FAISS vectorstore.
As seen in the github repo of FAISS I build an index like this and add vectors to it:
import faiss ...
4
votes
0
answers
451
views
Insert metadata Flowise + pinecone
I am trying to do an upsert in Pinecone using Flowise. As I need to do this for several PDF files, I am using the 'Folder with Files' node. So far so good, but I have the need to insert as metadata a ...
4
votes
0
answers
2k
views
ValueError: You are trying to offload the whole model to the disk. Please use the `disk_offload` function instead
I am trying to run a GitHub project on my computer.
GitHub Repo that I am trying to run
This is the code snippet that is causing errors.
Steps I took for replicating the project are:
Cloned the ...
4
votes
1
answer
3k
views
How do you use custom prompts with LangChains RetrievalQA without specifying from_chain_type?
According to LangChain's documentation,
"There are two ways to load different chain types. First, you can specify the chain type argument in the from_chain_type method. This allows you to pass in ...
4
votes
0
answers
447
views
Setting Up Multi-Host GPU Training Environment for SFTTrainer
I have a multi-host environment with the following GPU configuration:
Host1: GPU1
Host2: GPU2
Host3: GPU3, GPU4
Host4: GPU5, GPU6
To make sure that all available GPUs are used for training I'm using ...
4
votes
0
answers
155
views
Can an LLM with functions be used to solve a toy geometry problem?
I have constructed a toy problem that I would like to solve using an LLM like ChatGPT (and likely functions, langchain or something similar).
I have four locations (each location is a rectangle and ...
4
votes
1
answer
2k
views
RetrievalQA max token limit reached even though its short prompt
I am building a simple llm model which uses vectorstore embedding from the text file.
My prompt is very short, but whenever I request the answer from the model, I am getting a message that I have ...
4
votes
1
answer
2k
views
Cannot run MetaAI's llama2 due to "No module named 'fire'" error
I am trying to run the llama2 model locally on my MacOS (M1 chip).
In the example_chat_completion.py file there is an import for the fire module:
# Copyright (c) Meta Platforms, Inc. and affiliates.
# ...