[PR #3681] docs: add CRW integration (provider + document loader pages) #3713

Open
opened 2026-06-05 18:52:54 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/3681
Author: @us
Created: 4/22/2026
Status: 🔄 Open

Base: mainHead: add-crw-integration


📝 Commits (1)

  • e32336c docs: add CRW integration (provider + document loader pages)

📊 Changes

3 files changed (+145 additions, -0 deletions)

View changed files

📝 packages.yml (+4 -0)
src/oss/python/integrations/document_loaders/crw.mdx (+110 -0)
src/oss/python/integrations/providers/crw.mdx (+31 -0)

📄 Description

Summary

Adds documentation for the langchain-crw partner integration, per the guidance in langchain-ai/langchain#36273.

Changes

  • packages.yml: new entry for langchain-crw (follows the same pattern as langchain-scrapegraph / langchain-apify)
  • src/oss/python/integrations/providers/crw.mdx: provider page (modeled after the FireCrawl page)
  • src/oss/python/integrations/document_loaders/crw.mdx: document loader usage page (modeled after the FireCrawl page)

Context

CRW is an open-source, Firecrawl-compatible web scraper written in Rust. The CrwLoader in langchain-crw supports scrape, crawl, map, and search modes via BaseLoader with native lazy_load().

Related: langchain-ai/langchain#36273


🔄 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/3681 **Author:** [@us](https://github.com/us) **Created:** 4/22/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `add-crw-integration` --- ### 📝 Commits (1) - [`e32336c`](https://github.com/langchain-ai/docs/commit/e32336c2edda6ef72ac25345c8775557fd96704c) docs: add CRW integration (provider + document loader pages) ### 📊 Changes **3 files changed** (+145 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `packages.yml` (+4 -0) ➕ `src/oss/python/integrations/document_loaders/crw.mdx` (+110 -0) ➕ `src/oss/python/integrations/providers/crw.mdx` (+31 -0) </details> ### 📄 Description ## Summary Adds documentation for the `langchain-crw` partner integration, per the guidance in langchain-ai/langchain#36273. - PyPI: https://pypi.org/project/langchain-crw/ - GitHub: https://github.com/us/langchain-crw ## Changes - `packages.yml`: new entry for `langchain-crw` (follows the same pattern as `langchain-scrapegraph` / `langchain-apify`) - `src/oss/python/integrations/providers/crw.mdx`: provider page (modeled after the FireCrawl page) - `src/oss/python/integrations/document_loaders/crw.mdx`: document loader usage page (modeled after the FireCrawl page) ## Context CRW is an open-source, Firecrawl-compatible web scraper written in Rust. The `CrwLoader` in `langchain-crw` supports `scrape`, `crawl`, `map`, and `search` modes via `BaseLoader` with native `lazy_load()`. Related: langchain-ai/langchain#36273 --- <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 18:52:54 -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#3713