einSelbst / quivr

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

Quivr

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 [e-mail]: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