Reverse Dependencies of pgvector

The following projects have a declared dependency on pgvector:

• AdalFlow — The Library to Build and Auto-optimize LLM Applications
• adimis-graph-builder — Core utilities for the Adimis toolbox.
• agentstr — Tools for a Nostr agentic ecosystem
• agno — Agno: a lightweight framework for building multi-modal Agents
• aimbase — Declarative, instant REST APIs for base AI Models based on instarest, a FastAPI, Pydantic, SQLAlchemy, and PostgreSQL library, and MinIO.
• airbyte-destination-pgvector — Airbyte destination implementation for PGVector.
• alita-sdk — SDK for building langchain agents using resouces from Alita
• analysta-index — Extension of Langchain loaders, llms and retrievers for Analysta
• apache-airflow-providers-pgVector — Provider package apache-airflow-providers-pgvector for Apache Airflow
• article-rec-db — Database models and migrations for the Local News Lab's article recommendation system
• asyncdb — Library for Asynchronous data source connections Collection of asyncio drivers.
• autogen-agentchat-um — Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
• autologie — no summary
• bflower — A Python package with a built-in web application
• brdata-rag-tools — Improve development of retrieval augmented generation (RAG) applications at the BR AI + Automation Lab.
• brevia — Extensible API and framework to build your Retrieval Augmented Generation (RAG) and Information Extraction (IE) applications with LLMs
• chatdbt — chatdbt is an openai-based dbt documentation robot. You can use natural language to describe your data query requirements to the robot, and chatdbt will help you select the dbt model you need, or generate sql responses based on these dbt models to meet your need
• chem-mrl — SMILES-based Matryoshka Representation Learning Embedding Model
• cicada-agent — A Python package for the Cicada project
• cmbagent-autogen — A programming framework for agentic AI
• cognee — Cognee - is a library for enriching LLM context with a semantic layer for better understanding and reasoning.
• data-digitization — This SDK is for Data Digitization
• deputydev-cli — DeputyDev CLI is an AI-powered coding companion that streamlines software development with four core features: Code Generation to translate natural language into code, Documentation Generation for custom docstrings, Task Planning to structure development steps, and Test Generation for automated unit tests. This tool is designed to reduce development overhead and enhance coding productivity.
• dewy — Knowledge base service.
• dfapp — A Python package with a built-in web application
• dialog-lib — no summary
• digitization — This SDK is for Data Digitization.
• django-afpgvector — Package for handling postgres vector database
• django-embeddings — A Django application for embeddings
• django-langchain — Django Langchain
• django-pyhub-rag — Django app library for RAG integration
• django-torque-semantic-search — django app for torque semantic search
• docai-dev — DocAI Python module
• docailite — DocAI Lite Python module
• dsrag — State-of-the-art RAG pipeline from D-Star AI
• dynamiq — Dynamiq is an orchestration framework for agentic AI and LLM applications
• elroy — no summary
• flying-delta-legacy — Interface between LLMs and your data
• fudster — Fudster - A simple mL library for applications
• genius-agent — Create various chat agents based off YAML or JSON files of predefined configs
• genius-chatbot — Use huggingface models to create an intelligent and scalable chatbot
• graphtomation — An AI utility package to build and serve Crew and LangGraph workflows as FastAPI routes, packed with reusable components for AI engineers.
• griptape — Modular Python framework for LLM workflows, tools, memory, and data.
• iointel — A framework to create agents, tasks, and workflows.
• khoj — Your Second Brain
• kitab — A package for book recommendation.
• kozmoai — A Python package with a built-in web application
• kwwutils — Add your description here
• langchain_1111_Dev_cerebrum — Building applications with LLMs through composability
• langchain-by-johnsnowlabs — Building applications with LLMs through composability
• langchain-google-alloydb-pg — LangChain integrations for Google Cloud AlloyDB for PostgreSQL
• langchain-google-cloud-sql-pg — LangChain integrations for Google Cloud SQL for PostgreSQL
• langchain-postgres — An integration package connecting Postgres and LangChain
• langchain-xfyun — 在LangChain中流畅地使用讯飞星火大模型
• langchaincoexpert — Building applications with LLMs through composability
• langchainmsai — Building applications with LLMs through composability
• langchainn — Building applications with LLMs through composability
• langflow — A Python package with a built-in web application
• langflow-law — A Python package with a built-in web application
• langflow-nightly — A Python package with a built-in web application
• langgraph-studio — no summary
• langinfra — A Python package with a built-in web application
• langpack — A library to pakcage and deploy langugage model apps
• langplus — Building applications with LLMs through composability
• langroid — Harness LLMs with Multi-Agent Programming
• ldsi — LDSI
• letta — Create LLM agents with long-term memory and custom tools
• letta-nightly — Create LLM agents with long-term memory and custom tools
• lightrag — The Lightning Library for LLM Applications.
• llama-index-alloydb-pg — LlamaIndex integrations for Google Cloud AlloyDB for PostgreSQL
• llama-index-cloud-sql-pg — LlamaIndex integrations for Google Cloud SQL for PostgreSQL
• llama-index-legacy — Interface between LLMs and your data
• llama-index-vector-stores-postgres — llama-index vector_stores postgres integration
• llm-rag-builder — Это библиотека на Python, предназначенная для упрощения создания и управления моделями генерации с использованием поиска (Retrieval-Augmented Generation, RAG).
• LLMSmith — Lightweight Python library designed for developing functionalities powered by Large Language Models (LLMs)
• magic-assistant — An AI agent framework.
• mem-vault — A library for storing and retrieving embeddings with PGVector (with Chunking)
• mtmairoot — no summary
• mtmlib — no summary
• mypyautogen20240904 — Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
• nendo_plugin_library_postgres — PostgresDB implementation of the Nendo Library plugin. Comes with support for track embeddings.
• omnivector — .
• oplangchain — langchain for OpenPlugin
• pf-azuredb — Package for use in promptflow for vector search in azure db
• pgai — AI workflows in your PostgreSQL database
• PgDbToolkit — A package for managing PostgreSQL database operations
• pgvector-haystack — An integration of pgvector (vector search extension for Postgres) with Haystack
• pgvector-perf — Performance testing and benchmarking of pgvector
• pixeltable — AI Data Infrastructure: Declarative, Multimodal, and Incremental
• pleach — A Python package with a built-in web application
• postgres-rag — RAG (Retrieval-Augmented Generation) System
• postgresml-django — PostgresML Django integration that enables automatic embedding of specified fields.
• promptflow-vectordb — Prompt flow tools for accessing popular vector databases
• protein-metamorphisms-is — Comprehensive Python Module for Protein Data Management: Designed for streamlined integration and processing of protein information from both UniProt and PDB. Equipped with features for concurrent data fetching, robust error handling, and database synchronization.
• py_nl2sql — A toolkit for converting natural language to SQL statements.
• PyAutoGen — A programming framework for agentic AI
• pydevgpt — Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
• pyjolt — A batteries included async-first python webframework
• pymemgpt — Create LLM agents with long-term memory and custom tools
• pymemgpt-nightly — Create LLM agents with long-term memory and custom tools