langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-22 12:25:55 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[PR #3844] Add Keiro integration docs (retriever, embeddings, search tool) #3862

New Issue
Open
opened 2026-06-05 18:53:24 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 18:53:24 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/3844
Author: @Manasbh
Created: 5/2/2026
Status: 🔄 Open

Base: main ← Head: add-keiro-integration

📝 Commits (2)

  • 1984310 Add Keiro integration docs (retriever, embeddings, search tool)
  • be1781a Merge branch 'main' into add-keiro-integration

📊 Changes

3 files changed (+323 additions, -0 deletions)

View changed files

➕ src/oss/python/integrations/embeddings/keiro.mdx (+108 -0)
➕ src/oss/python/integrations/retrievers/keiro.mdx (+113 -0)
➕ src/oss/python/integrations/tools/keiro_search.mdx (+102 -0)

📄 Description

Summary

Add documentation for the langchain-keiro integration package.

What Keiro does

Keiro's deep search endpoint (/v2/search/content) returns full page content, AI-generated summaries, structured metadata (tags, entities, credibility), and embedding vectors all in a single API call. This eliminates the need for a separate embedding model in RAG pipelines — search and embed in one step.

Three components, one endpoint

All three classes call the same Keiro API endpoint with mode: "deep" and embeddings: {enabled: true}. The difference is what they return:

  • KeiroRetriever — Returns LangChain Document objects with the full search result (page content, title, source URL, summary, tags, entities, credibility score) plus embeddings baked into metadata. Use this in RAG chains where you need both retrieved content and vectors.

  • KeiroEmbeddings — Returns only the embedding vectors. Same API call under the hood, but strips out the document content and metadata. Implements the Embeddings interface so you can drop it into any LangChain pipeline that expects an embedding model (vector stores, similarity search, etc.). Supports Matryoshka dimensions (384, 512, 768, 1024).

  • KeiroSearchTool — Returns formatted search results as a string. Designed for LangChain agents that need to search the web and get human-readable output. Implements the BaseTool interface with proper input schema.

Why this over Tavily/SerpAPI

  • Embeddings included: No other search API returns embedding vectors. With Tavily or SerpAPI you need a separate embedding model and an extra API call. Keiro gives you both in one request.
  • Structured metadata: Tags, named entities, credibility scores, AI summaries come free with every result.
  • Matryoshka dimensions: Choose 384/512/768/1024 dims to trade precision for speed and storage.
  • Serializable: All three classes implement is_lc_serializable() for LangSmith tracing.

Package info

Files added

  • src/oss/python/integrations/retrievers/keiro.mdx
  • src/oss/python/integrations/embeddings/keiro.mdx
  • src/oss/python/integrations/tools/keiro_search.mdx

Each follows the official integration doc template with Overview, Integration details, Features, Setup, Instantiation, and Invocation sections.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/docs/pull/3844 **Author:** [@Manasbh](https://github.com/Manasbh) **Created:** 5/2/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-keiro-integration` --- ### 📝 Commits (2) - [`1984310`](https://github.com/langchain-ai/docs/commit/198431078288f1ad224643c60f89874264d8dc35) Add Keiro integration docs (retriever, embeddings, search tool) - [`be1781a`](https://github.com/langchain-ai/docs/commit/be1781a98242c28ee6a250919fd79ec52034dffe) Merge branch 'main' into add-keiro-integration ### 📊 Changes **3 files changed** (+323 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `src/oss/python/integrations/embeddings/keiro.mdx` (+108 -0) ➕ `src/oss/python/integrations/retrievers/keiro.mdx` (+113 -0) ➕ `src/oss/python/integrations/tools/keiro_search.mdx` (+102 -0) </details> ### 📄 Description ## Summary Add documentation for the `langchain-keiro` integration package. ### What Keiro does Keiro's deep search endpoint (`/v2/search/content`) returns full page content, AI-generated summaries, structured metadata (tags, entities, credibility), and embedding vectors all in a single API call. This eliminates the need for a separate embedding model in RAG pipelines — search and embed in one step. ### Three components, one endpoint All three classes call the same Keiro API endpoint with `mode: "deep"` and `embeddings: {enabled: true}`. The difference is what they return: - **KeiroRetriever** — Returns LangChain `Document` objects with the full search result (page content, title, source URL, summary, tags, entities, credibility score) plus embeddings baked into metadata. Use this in RAG chains where you need both retrieved content and vectors. - **KeiroEmbeddings** — Returns only the embedding vectors. Same API call under the hood, but strips out the document content and metadata. Implements the `Embeddings` interface so you can drop it into any LangChain pipeline that expects an embedding model (vector stores, similarity search, etc.). Supports Matryoshka dimensions (384, 512, 768, 1024). - **KeiroSearchTool** — Returns formatted search results as a string. Designed for LangChain agents that need to search the web and get human-readable output. Implements the `BaseTool` interface with proper input schema. ### Why this over Tavily/SerpAPI - **Embeddings included**: No other search API returns embedding vectors. With Tavily or SerpAPI you need a separate embedding model and an extra API call. Keiro gives you both in one request. - **Structured metadata**: Tags, named entities, credibility scores, AI summaries come free with every result. - **Matryoshka dimensions**: Choose 384/512/768/1024 dims to trade precision for speed and storage. - **Serializable**: All three classes implement `is_lc_serializable()` for LangSmith tracing. ### Package info - **PyPI**: https://pypi.org/project/langchain-keiro/ - **Source**: https://github.com/Keirolabs-API/langchain-keiro - **Standard tests**: Passes `langchain-tests` EmbeddingsUnitTests and ToolsUnitTests ## Files added - `src/oss/python/integrations/retrievers/keiro.mdx` - `src/oss/python/integrations/embeddings/keiro.mdx` - `src/oss/python/integrations/tools/keiro_search.mdx` Each follows the official integration doc template with Overview, Integration details, Features, Setup, Instantiation, and Invocation sections. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 18:53:24 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#3862
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?