NewsCatcher CatchAll Integration

[oleksandrsirenko]

Overview

Adds integration documentation for NewsCatcher CatchAll, a web search API that finds distributed real-world events across millions of sources and returns structured data. The integration includes both programmatic client access and agent toolkit for LangGraph workflows.

Type of change

Type: New documentation page

Related issues/PRs

• GitHub issue: N/A (first-time contribution)
• Feature PR: N/A (integration package already published to PyPI)

Checklist

• I have read the contributing guidelines
• I have tested my changes locally using make dev
• All code examples have been tested and work correctly
• I have used root relative paths for internal links
• I have updated navigation in index files (tools/index.mdx and providers/all_providers.mdx)

Additional notes

Files Added/Modified

1. Tool documentation (docs/src/oss/python/integrations/tools/newscatcher_catchall.mdx)

   • Complete setup and installation instructions
   • Three invocation patterns: direct, ToolCall, and within agent
   • Real-world examples tested with actual API
   • Agent-specific features and optimization patterns

2. Provider documentation (docs/src/oss/python/integrations/providers/newscatcher.mdx)

   • CatchAllClient for programmatic access
   • Async support for concurrent operations
   • Cost optimization patterns
   • Links to tool documentation

3. Tools index (docs/src/oss/python/integrations/tools/index.mdx)

   • Added card in alphabetical order (between Naver and Nuclia)
   • Added table row with pricing and return data info

4. Providers index (docs/src/oss/python/integrations/providers/all_providers.mdx)

   • Added card in alphabetical order (between Naver and Neo4j)

Package Information

• Package name: langchain-catchall
• PyPI: https://pypi.org/project/langchain-catchall/
• GitHub: https://github.com/NewscatcherAPI/langchain-catchall
• Full documentation: https://www.newscatcherapi.com/docs/v3/catch-all/integrations/langchain

Testing Details

• Local build completed successfully (make build)
• Dev server verified all pages render correctly (make dev)
• Navigation tested: cards and table entries appear in correct alphabetical positions
• All internal links verified (no 404s)
• All external links tested and functional
• Code examples tested with live API (examples use real query results)

Note on Deprecation

Examples use langgraph.prebuilt.create_react_agent which shows a deprecation warning in LangGraph v1.0+. This is intentional, as the new langchain.agents.create_agent has not been tested with this integration yet.

[github-actions]

❌ Import check failed

This PR contains imports from langchain_core that should be imported from langchain instead.

Detailed issues

Analyzing diff for import issues...
 Found 2 import issues:

File: src/oss/python/integrations/providers/newscatcher.mdx
Line: 151
Issue: Import from langchain.messages instead of langchain_core.messages
Current:   from langchain_core.messages import SystemMessage
Suggested: from langchain.messages import SystemMessage
--------------------------------------------------------------------------------
File: src/oss/python/integrations/tools/newscatcher_catchall.mdx
Line: 143
Issue: Import from langchain.messages instead of langchain_core.messages
Current:   from langchain_core.messages import SystemMessage
Suggested: from langchain.messages import SystemMessage
--------------------------------------------------------------------------------

 Found 2 import issues that need to be fixed.

Why this is a problem

The langchain package re-exports many modules and classes from langchain_core. When possible, imports should use langchain instead of langchain_core for:

• Better user experience (single import source)
• Consistency across documentation
• Reduced cognitive load for users

How to fix

Replace the imports as suggested above. For example:

• ❌ from langchain_core.messages import HumanMessage
• ✅ from langchain.messages import HumanMessage

🤖 Automated check

This check is based on the latest analysis of langchain re-exports from langchain_core.