Langchain Embeddings Search

What it does

When your agent uses it

• Building a RAG pipeline
• Choosing between FAISS / Pinecone / Chroma / PGVector
• Filtering by similarity score
• Adding a reranker

Example prompts

• “langchain embeddings”
• “vector store similarity search”
• “langchain RAG retrieval”
• “/langchain-embeddings-search”

Requirements

• Python 3
• A credential in OPENAI_API_KEY
• A credential in PINECONE_API_KEY
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(python:*), Bash(pip:*), Grep

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Initialize embeddings with an explicit dim
2. 2Choose a vector store
3. 3Normalize scores before any threshold filter
4. 4Chunk text with language-aware splitters
5. 5Hybrid search (keyword + vector)
6. 6Rerank by rank, not by score

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash(python:*)
  • Bash(pip:*)
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • python.langchain.com
  • github.com
  • docs.pinecone.io
  • docs.cohere.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OPENAI_API_KEY
  • PINECONE_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Langchain Embeddings Search loads about 2.6k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 122 tokens; SKILL.md has 802 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~122

When it runs · the whole SKILL.md, loaded when a task matches

~2.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 802 words, ~2,551 tokens.

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".

allowed-tools

Read, Write, Edit, Bash(python:*), Bash(pip:*), Grep

compatibility

Designed for Claude Code

version

2.7.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, langchain, python, langchain-1.0, embeddings, rag, vector-store

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-small",  # 1536 dims
    # For text-embedding-3-large, use 3072 dims — must match index
)

# Assert dim at startup (prevents P14)
assert len(embeddings.embed_query("test")) == 1536, "embedding dim drifted"

from langchain_community.vectorstores import FAISS

store = FAISS.from_documents(docs, embedding=embeddings)
results = store.similarity_search_with_score("query", k=5)
# FAISS: [(doc, 0.31), (doc, 0.42), ...] — LOWER IS MORE SIMILAR

from langchain_pinecone import PineconeVectorStore

store = PineconeVectorStore(index_name="prod", embedding=embeddings)
results = store.similarity_search_with_score("query", k=5)
# Pinecone: [(doc, 0.91), (doc, 0.87), ...] — HIGHER IS MORE SIMILAR

def normalize(score: float, store_type: str) -> float:
    """Return similarity in [0, 1] where 1 = identical, 0 = unrelated."""
    if store_type == "faiss_l2":
        return 1.0 / (1.0 + score)  # collapse L2 distance into similarity
    if store_type in {"pinecone", "chroma", "pgvector"}:
        return max(0.0, min(1.0, score))  # already similarity, clamp just in case
    raise ValueError(f"Unknown store type: {store_type}")

from langchain_text_splitters import RecursiveCharacterTextSplitter, Language

# BAD — breaks inside Markdown code fences (P13)
bad = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)

# GOOD — respects Markdown structure
md_splitter = RecursiveCharacterTextSplitter.from_language(
    Language.MARKDOWN, chunk_size=1000, chunk_overlap=100,
)

# For Python source files
py_splitter = RecursiveCharacterTextSplitter.from_language(
    Language.PYTHON, chunk_size=1500, chunk_overlap=150,
)

from langchain.retrievers import EnsembleRetriever
from langchain_community.retrievers import BM25Retriever

bm25 = BM25Retriever.from_documents(docs); bm25.k = 5
vector = store.as_retriever(search_kwargs={"k": 5})

ensemble = EnsembleRetriever(
    retrievers=[bm25, vector],
    weights=[0.4, 0.6],  # tune on your eval set
)

from langchain_cohere import CohereRerank

reranker = CohereRerank(top_n=3, model="rerank-v3.5")
reranked = reranker.compress_documents(
    documents=candidates, query=query,
)
# reranked[0].metadata["relevance_score"] is query-relative — 0.34 may be the best
# WRONG: [d for d in reranked if d.metadata["relevance_score"] > 0.5]
# RIGHT: reranked[:top_n]  — trust the rank order

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/.curated/langchain-embeddings-search of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/hybrid-search.md
• references/one-pager.md
• references/score-semantics.md
• references/vector-store-comparison.md

Open the folder on GitHubat commit cfae287