langchain-embeddings-search
Best for RAG pipeline developersWorks with GitHub
⌘source
- author
@jeremylongshore- language
- Python
★2kstars
268forks
Apr 22, 2026
✦overview.md
Key Features
- ·Avoids flipped score semantics between FAISS and Pinecone
- ·Addresses embedding-dimension mismatches
- ·Handles reranker quirks
- ·Fixes chunk-splitter bugs in Markdown code fences
- ·Works with FAISS, Pinecone, Chroma, and PGVector
- ·Supports similarity score filtering
Use Cases
- →Building a RAG pipeline
- →Choosing between FAISS, Pinecone, Chroma, or PGVector vector stores
- →Filtering search results by similarity score
- →Adding a reranker to your retrieval system
- →Migrating from FAISS to Pinecone without losing retrieval quality
Best for
- ✓RAG pipeline developers
- ✓Teams migrating between vector stores
- ✓Projects using LangChain 1.0
Not ideal for
- !Non-Python environments
- !LangChain versions before 1.0
FAQs
name
langchain-embeddings-search
description
Build and query vector stores with LangChain 1.0 without getting burned by
flipped score semantics, embedding-dim mismatches, reranker quirks, and
chunk-splitter bugs. Use when building a RAG pipeline, choosing between FAISS /
Pinecone / Chroma / PGVector, filtering by similarity score, or adding a reranker.
Trigger with "langchain embeddings", "vector store similarity search",
"langchain RAG retrieval", "FAISS score", "Pinecone score", "reranker score".
license
MIT
allowed-tools:Read, Write, Edit, Bash(python:*), Bash(pip:*), Grep
version:2.0.0
author:Jeremy Longshore <jeremy@intentsolutions.io>
tags:["saas","langchain","python","langchain-1.0","embeddings","rag","vector-store"]
compatible-with:claude-code, codex
LangChain Embeddings and Vector Search (Python)
Overview
FAISS.similarity_search_with_score() returns L2 distance — lower is better.
Pinecone.similarity_search_with_score() returns cosine similarity — higher is
better. Swap your vector store and your if score > 0.8 filter now keeps the
garbage and drops the good results, silently. This is pain-catalog entry P12,
and it is the single most common reason a "we migrated from FAISS to Pinecone
for scale" project loses retrieval quality overnight.
The sibling gotchas:
- P13 —
RecursiveCharacterTextSplitterdefault separators break inside code fences, so RAG over Markdown docs truncates code examples mid-function - P14 — Embedding-dim mismatch crashes at insert time (after 10 minutes of
processing), not at
VectorStore.__init__; the failure blames "dim mismatch: 1536 != 3072" and no earlier error - P15 — Cohere/Jina reranker scores are within-query relative, so a 0.34 top-1 is not worse than a 0.92 top-1 on a different query; filtering by threshold is the wrong heuristic
This skill walks through embedding model selection, vector store creation with
$install
1-click copynpx skills add jeremylongshore/claude-code-plugins-plus-skills --skill langchain-embeddings-searchSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.