Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

LangChain embeddings and vector search v1.0.0

Use this resource to build and query a vector store with LangChain 1.0

New

  • 498 downloads
  • 153 likes
  • 192 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install langchain-vector-search-scores

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent sets embeddings with an explicit dimension, picks between FAISS, Pinecone, Chroma or PGVector and normalizes scores before any threshold filter. It adds Markdown-aware chunking and, when needed, a reranker.

Mostly picked by

Updated November 2, 2026

Card for the “LangChain embeddings and vector search” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: setup steps and pitfalls to avoid
  • references/score-semantics.md: how scores behave in each store
  • references/vector-store-comparison.md and references/hybrid-search.md: comparison and hybrid search

Good fit for

  • Your retrieval quality dropped after moving from FAISS to Pinecone
  • You are building a RAG pipeline that filters by similarity score

Not for

    Tags

    • langchain
    • embeddings
    • rag
    • vectors
    • retrieval

    About

    You say

    “Set up LangChain vector search over my Markdown docs with a similarity threshold that actually works.”

    Card for the “LangChain embeddings and vector search” skill

    Skill published by Jeremy Longshore <jeremy@intentsolutions.io> under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to build and query a vector store with LangChain 1.0
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.6 KB
    • references/hybrid-search.md4.1 KB
    • references/one-pager.md3 KB
    • references/score-semantics.md4.7 KB
    • references/vector-store-comparison.md4.3 KB
    • SKILL.md10.3 KB

    Origin and licence

    Listed unmodified

    Author
    Jeremy Longshore <jeremy@intentsolutions.io>
    Source
    github.com/jeremylongshore/tons-of-skills-marketplace/tree/ab85a061f7bcc039dac13ee193de7a4cd4388571/skills/.curated/langchain-embeddings-search
    Licence
    MIT

    Notice

    « langchain-embeddings-search » (Jeremy Longshore <jeremy@intentsolutions.io>, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.