/quivr

Dump all your files and thoughts into your GenerativeAI Second Brain and chat with it

Primary LanguagePythonApache License 2.0Apache-2.0

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

quiver-16.05.mp4

Demo with Claude 100k context

Quivr.webm

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 $$
           # variable_conflict use_column
       BEGIN
           RETURN query
           SELECT
               id,
               content,
               metadata,
               embedding,
               1 -(documents.embedding <=> query_embedding) AS similarity
           FROM
               documents
           ORDER BY
               documents.embedding <=> query_embedding
           LIMIT match_count;
       END;
       $$;

and

create table
  stats (
    -- A column called "time" with data type "timestamp"
    time timestamp,
    -- A column called "details" with data type "text"
    chat boolean,
    embedding boolean,
    details text,
    metadata jsonb,
    -- An "integer" primary key column called "id" that is generated always as identity
    id integer primary key generated always as identity
  );
  • 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