基于 Quivr 搭建个人专属知识库

git clone https://github.com/StanGirard/quivr.git && cd quivr
# 切换到 v0.0.4分支
git checkout v0.0.4
git checkout -b v0.0.4

cp .backend_env.example backend/.env
cp .frontend_env.example frontend/.env

create extension vector;

-- Create a table to store your documents
create table if not exists 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 $$
    # variable_conflict use_column
BEGIN
    RETURN query
    SELECT
        id,
        content,
        metadata,
        embedding,
        1 -(documents.embedding <=> query_embedding) AS similarity
    FROM
        documents
    ORDER BY
        documents.embedding <=> query_embedding
    LIMIT match_count;
END;
$$;

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
  );

-- Create a table to store your summaries
create table if not exists summaries (
    id bigserial primary key,
    document_id bigint references documents(id),
    content text, -- corresponds to the summarized content
    metadata jsonb, -- corresponds to Document.metadata
    embedding vector(1536) -- 1536 works for OpenAI embeddings, change if needed
);

CREATE OR REPLACE FUNCTION match_summaries(query_embedding vector(1536), match_count int, match_threshold float)
    RETURNS TABLE(
        id bigint,
        document_id bigint,
        content text,
        metadata jsonb,
        -- we return matched vectors to enable maximal marginal relevance searches
        embedding vector(1536),
        similarity float)
    LANGUAGE plpgsql
    AS $$
    # variable_conflict use_column
BEGIN
    RETURN query
    SELECT
        id,
        document_id,
        content,
        metadata,
        embedding,
        1 -(summaries.embedding <=> query_embedding) AS similarity
    FROM
        summaries
    WHERE 1 - (summaries.embedding <=> query_embedding) > match_threshold
    ORDER BY
        summaries.embedding <=> query_embedding
    LIMIT match_count;
END;
$$;

# Uninstall old versions
sudo yum remove docker \
                  docker-client \
                  docker-client-latest \
                  docker-common \
                  docker-latest \
                  docker-latest-logrotate \
                  docker-logrotate \
                  docker-engine

# Set up the repository
sudo yum install -y yum-utils
sudo yum-config-manager --add-repo https://download.docker.com/linux/centos/docker-ce.repo

# Install Docker Engine
sudo yum install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin

# Start Docker
sudo systemctl start docker

docker compose build && docker compose up