🧠 Dump all your files and chat with it using your Generative AI Second Brain using LLMs ( GPT 3.5/4, Private, Anthropic, VertexAI ) & Embeddings 🧠
Go to file
2023-05-17 16:26:25 +02:00
.github/workflows feat(releaseplease): added 2023-05-16 16:25:08 +02:00
.streamlit feat(demo): app can now have a demo 2023-05-17 12:12:52 +02:00
.vscode Support for Anthropics Models 2023-05-14 01:30:03 -07:00
loaders fix(demo): max size audio 2023-05-17 12:18:55 +02:00
website docs(website): added demo link 2023-05-17 14:44:57 +02:00
.gitignore feat(website): first iteration 2023-05-14 21:12:30 +02:00
2023-05-13-02-16-02.png feat(demo): added 2023-05-13 02:16:41 +02:00
brain.py feat(forget): now able to forget things 2023-05-13 01:30:00 +02:00
Dockerfile fix(requirements): fixed the issue 2023-05-13 16:37:18 +02:00
explorer.py feat(explorer): beta 2023-05-16 17:04:45 +02:00
files.py fix(demo): remove multi file upload 2023-05-17 16:26:25 +02:00
LICENSE feat(license): added 2023-05-13 18:12:35 +02:00
logo.png feat(readme): first iteration 2023-05-13 02:02:45 +02:00
main.py doc(demo): made it more visual 2023-05-17 12:53:36 +02:00
question.py feat(demo): app can now have a demo 2023-05-17 12:12:52 +02:00
README.md Update README.md (#40) 2023-05-17 00:14:13 +02:00
requirements.txt Support for Anthropics Models 2023-05-14 01:30:03 -07:00
sidebar.py feat(visual): moved things around 2023-05-12 23:58:19 +02:00
stats.py feat(demo): app can now have a demo 2023-05-17 12:12:52 +02:00
utils.py feat(init): init repository 2023-05-12 23:05:31 +02:00

Quivr

Quivr-logo

Join our Discord

Quivr is your second brain in the cloud, designed to easily store and retrieve unstructured information. It's like Obsidian but powered by generative AI.

Features

  • Store Anything: Quivr can handle almost any type of data you throw at it. Text, images, code snippets, you name it.
  • Generative AI: Quivr uses advanced AI to help you generate and retrieve information.
  • Fast and Efficient: Designed with speed and efficiency in mind. Quivr makes sure you can access your data as quickly as possible.
  • Secure: Your data is stored securely in the cloud and is always under your control.
  • Compatible Files:
    • Text
    • Markdown
    • PDF
    • Audio
    • Video
  • Open Source: Quivr is open source and free to use.

Demo

Demo with GPT3.5

https://github.com/StanGirard/quivr/assets/19614572/80721777-2313-468f-b75e-09379f694653

Demo with Claude 100k context

https://github.com/StanGirard/quivr/assets/5101573/9dba918c-9032-4c8d-9eea-94336d2c8bd4

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Prerequisites

What things you need to install the software and how to install them.

  • Python 3.10 or higher
  • Pip
  • Virtualenv
  • Supabase account
  • Supabase API key
  • Supabase URL

Installing

  • Clone the repository
git clone git@github.com:StanGirard/Quivr.git & cd Quivr
  • Create a virtual environment
virtualenv venv
  • Activate the virtual environment
source venv/bin/activate
  • Install the dependencies
pip install -r requirements.txt
  • Copy the streamlit secrets.toml example file
cp .streamlit/secrets.toml.example .streamlit/secrets.toml
  • Add your credentials to .streamlit/secrets.toml file
supabase_url = "SUPABASE_URL"
supabase_service_key = "SUPABASE_SERVICE_KEY"
openai_api_key = "OPENAI_API_KEY"
anthropic_api_key = "ANTHROPIC_API_KEY" # Optional
  • Run the migration script on the Supabase database via the web interface
-- Enable the pgvector extension to work with embedding vectors
       create extension vector;

       -- Create a table to store your documents
       create table documents (
       id bigserial primary key,
       content text, -- corresponds to Document.pageContent
       metadata jsonb, -- corresponds to Document.metadata
       embedding vector(1536) -- 1536 works for OpenAI embeddings, change if needed
       );

       CREATE FUNCTION match_documents(query_embedding vector(1536), match_count int)
           RETURNS TABLE(
               id bigint,
               content text,
               metadata jsonb,
               -- we return matched vectors to enable maximal marginal relevance searches
               embedding vector(1536),
               similarity float)
           LANGUAGE plpgsql
           AS $$
           # variable_conflict use_column
       BEGIN
           RETURN query
           SELECT
               id,
               content,
               metadata,
               embedding,
               1 -(documents.embedding <=> query_embedding) AS similarity
           FROM
               documents
           ORDER BY
               documents.embedding <=> query_embedding
           LIMIT match_count;
       END;
       $$;
  • Run the app
streamlit run main.py

Built With

  • Python - The programming language used.
  • Streamlit - The web framework used.
  • Supabase - The open source Firebase alternative.

Contributing

Open a pull request and we'll review it as soon as possible.

Star History

Star History Chart