[PR #3034] docs: add HighSNR compressor integration #3114

Open
opened 2026-06-05 18:21:08 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/3034
Author: @georgeSkoumas
Created: 3/10/2026
Status: 🔄 Open

Base: mainHead: feat/highsnr-integration


📝 Commits (2)

  • 2e4887e docs: add HighSNR compressor integration
  • 52063b1 docs: update benchmark numbers to Claude Sonnet 4.5 results

📊 Changes

1 file changed (+97 additions, -0 deletions)

View changed files

src/oss/python/integrations/retrievers/highsnr-compressor.mdx (+97 -0)

📄 Description

Closes #3033

Summary

Add documentation for langchain-highsnr, a
deterministic context optimizer that compresses documents to a token budget, keeping the
highest-signal content.

New page at src/oss/python/integrations/retrievers/highsnr-compressor.mdx covering:

  • HighSNRDocumentCompressor — post-retrieval compression via ContextualCompressionRetriever
  • HighSNRDocumentTransformer — pre-indexing compression before embedding
  • Parameter tables for both components
  • Benchmark summary with link to reproduction scripts

🔄 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/3034 **Author:** [@georgeSkoumas](https://github.com/georgeSkoumas) **Created:** 3/10/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `feat/highsnr-integration` --- ### 📝 Commits (2) - [`2e4887e`](https://github.com/langchain-ai/docs/commit/2e4887eb0bddbe6ffb653933257d82ecb5ceccb5) docs: add HighSNR compressor integration - [`52063b1`](https://github.com/langchain-ai/docs/commit/52063b14d54cfa71348e25a612885abee5ada7e8) docs: update benchmark numbers to Claude Sonnet 4.5 results ### 📊 Changes **1 file changed** (+97 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `src/oss/python/integrations/retrievers/highsnr-compressor.mdx` (+97 -0) </details> ### 📄 Description Closes #3033 ## Summary Add documentation for [langchain-highsnr](https://pypi.org/project/langchain-highsnr/), a deterministic context optimizer that compresses documents to a token budget, keeping the highest-signal content. New page at `src/oss/python/integrations/retrievers/highsnr-compressor.mdx` covering: - `HighSNRDocumentCompressor` — post-retrieval compression via `ContextualCompressionRetriever` - `HighSNRDocumentTransformer` — pre-indexing compression before embedding - Parameter tables for both components - Benchmark summary with link to reproduction scripts --- <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 18:21:08 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#3114