MerchantryTidbits

Public catalog

rag-retrieval

43 shown. Search ranks against problem language; browsing defaults to stronger public signals.

rag-retrievalclilocal

open-webui

self-host ChatGPT-like UI over local models

Verified 2026-08-10 · 27,370 stars

rag-retrievalclifree

qdrant

self-hosted vector search for embeddings

Verified 2026-08-10 · 16,001 stars

rag-retrievalclifree

meilisearch

typo-tolerant open-source search engine

Verified 2026-08-10 · 13,934 stars

rag-retrievallibraryfree

chroma

local vector database for RAG embeddings

Verified 2026-08-10 · 13,712 stars

rag-retrievallibraryfree

dspy

optimize LLM prompts and pipelines programmatically

Verified 2026-08-10 · 12,108 stars

rag-retrievallibraryfree

llama-index

RAG index from documents

Verified 2026-08-10 · 11,904 stars

rag-retrievallibrarylocal

faiss

in-process similarity search over embeddings

Verified 2026-08-10 · 10,735 stars

rag-retrievalclifree

typesense

typo-tolerant search engine for product catalogs

Verified 2026-08-10 · 6,614 stars

rag-retrievalclilocal

text-embeddings-inference

use text-embeddings-inference for rag retrieval

Verified 2026-08-10 · 2,251 stars

rag-retrievallibraryfree

Zep

agent needs long-term memory across sessions

Verified 2026-08-10 · 2,203 stars

rag-retrievallibraryfree

TruLens

need offline evals for LLM app quality

Verified 2026-08-10 · 1,647 stars

rag-retrievallibraryfree

FastEmbed

need fast local embeddings without heavy torch

Verified 2026-08-10 · 1,000 stars

rag-retrievallibraryfree

FlashRank

use FlashRank for rag retrieval

Verified 2026-08-10 · 991 stars

rag-retrievallibraryfree

chonkie

chunk documents for RAG without destroying structure

Verified 2026-08-10 · 611 stars

rag-retrievallibraryfree

Qdrant Client

Python client for self-hosted Qdrant vectors

Verified 2026-08-10 · 572 stars

rag-retrievallibraryfree

express-session

use express-session for rag retrieval

Verified 2026-08-10 · 399 stars

rag-retrievallibraryfree

Open WebUI Pipelines

extend Open WebUI with filter pipelines

Verified 2026-08-10 · 206 stars

rag-retrievallibraryfree

connect-redis

use connect-redis for rag retrieval

Verified 2026-08-10 · 106 stars

rag-retrievallibraryfree

Batched

batch embedding requests to cut API cost

Verified 2026-08-10 · 1 stars

rag-retrievalappfree

AnythingLLM

stand up private document chat without assembling a RAG stack

Verified 2026-08-10

rag-retrievallibrarylocal

EmbedAnything

I need to create local embeddings from a PDF without building separate ingestion code.

Verified 2026-08-10

rag-retrievallibraryfree

Embedchain

prototype document ingestion and question answering with minimal glue

Verified 2026-08-10

rag-retrievallibrarylocal

flag-embedding

use flag-embedding for rag retrieval

Verified 2026-08-10

rag-retrievallibraryapi_key

GraphRAG

find relationships among entities and themes across a research corpus

Verified 2026-08-10

rag-retrievallibraryfree

Haystack

compose typed retrieval and generation components into a pipeline

Verified 2026-08-10

rag-retrievalapplocal

Langchain-Chatchat

You must offer chat Q and A over internal documents and can configure the entire pipeline to use local inference frameworks, local models, and local stores so document-derived content stays on your infrastructure

Verified 2026-08-10

rag-retrievalmcpfree

mcp-youtube-transcript

give an MCP client timestamped YouTube transcript text

Verified 2026-08-10

rag-retrievalmcpfree

NotebookLM MCP Server

Your agent needs cited, grounded answers from Google NotebookLM notebooks but NotebookLM offers no public API

Verified 2026-08-10

rag-retrievalclilocal

Open Notebook

open-source notebook LM style research notes

Verified 2026-08-10

rag-retrievalclilocal

open-science

use open-science for rag retrieval

Verified 2026-08-10

rag-retrievallibraryfree

OpenInference

standardize LLM span attributes across frameworks

Verified 2026-08-10

rag-retrievalclilocal

pdf-brain

Your research papers, books, and Obsidian notes are scattered across folders and you want one semantically searchable knowledge base without paying for embedding APIs

Verified 2026-08-10

rag-retrievallibrarylocal

pgvector

Your application data already lives in Postgres and you need nearest neighbor search over embeddings without operating a separate vector database

Verified 2026-08-10

rag-retrievalappfree

PrivateGPT

run document question answering without sending files to a hosted service

Verified 2026-08-10

rag-retrievallibrarylocal

Qwen3-VL-Embedding & Reranker

You need to search a corpus of images, screenshots, PDF page renders, or videos with natural language queries in one shared vector space

Verified 2026-08-10

rag-retrievallibraryfree

ragatouille

use ragatouille for rag retrieval

Verified 2026-08-10

rag-retrievalcliapi_key

SemTools

You want to grep a folder of text or markdown files by meaning rather than exact keywords, straight from the terminal without standing up a vector database

Verified 2026-08-10

rag-retrievallibraryfree

Sentence Transformers

local embedding models for semantic search

Verified 2026-08-10

rag-retrievallibrarylocal

SQLite-Vector

A mobile or edge app needs offline semantic search over embeddings and running a separate vector database server is not an option

Verified 2026-08-10

rag-retrievallibraryfree

txtai

add semantic search to a Python dataset with a small API

Verified 2026-08-10

rag-retrievallibrarylocal

UltraRAG

You are prototyping iterative RAG logic with loops and conditional branches and writing the orchestration code by hand is dominating the work

Verified 2026-08-10

rag-retrievallibrarylocal

VectorChord

Your pgvector index build and query latency have become unworkable now that the table holds tens or hundreds of millions of embeddings

Verified 2026-08-10

rag-retrievalapifree

Weaviate

Your semantic search corpus has outgrown an in-memory or embedded vector store and needs replication, horizontal scaling, and RBAC

Verified 2026-08-10