Skip to content

s9kt/deep-research-langchain

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Pranav's Deep Research AI

I used to have a Claude Subscription, and then it ran out and I lost the "deep research" feature. I figured that it would be worth a shot to create my own Deep Research tool. Hence, I vibe coded and then patched up this python project. I chose to use Together.ai for the API because I already had it, but any OpenAI compatible API will suffice. Registering for everything else is ez. PubMed just needs your email.

Repo setup

Clone repo:

git clone https://github.com/s9kt/deep-research-langchain.git

Init virtual environment (conda or mamba if you prefer):

conda create -n deep_research_agent python=3.10
conda activate deep_research_agent

Install requirements:

pip install -r requirements.txt

Run app

python app.py

Setup for Open-WebUI:

I recommend running this with Open-WebUI for good UX, but any chat interface that can connect to a localhost IP will do. Once you have Open-WebUI functioning, continue.

Admin Panel -> Settings -> Connections -> Manage OpenAI API Connections

  • Connection Type: Internal
  • URL: http://localhost:PORT/v1 or http://host.docker.internal:PORT/v1 for docker

Verify connection to ensure it connects.

Search in the model menu, you should see it.

About

Wanted to have my own deep research AI so I vibe coded a python script that uses langchain

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages