This PR adds three powerful new memory methods that significantly improve the developer experience for populating Langbase memory from various content sources.

New Methods

memories.uploadText()

Upload text content directly to memory without file handling:

await langbase.memories.uploadText({
 memoryName: 'my-memory',
 text: 'Your content here...',
 documentName: 'optional-name.txt', // Auto-generates if not provided
 meta: { type: 'user-content' }
});

memories.uploadFromSearch()

Search the web and upload results directly to memory:

await langbase.memories.uploadFromSearch({
 memoryName: 'research-memory',
 query: 'What is artificial intelligence?',
 service: 'exa',
 totalResults: 5,
 apiKey: 'your-exa-key',
 documentNamePrefix: 'ai-research'
});

memories.uploadFromCrawl()

Crawl URLs and upload content directly to memory:

await langbase.memories.uploadFromCrawl({
 memoryName: 'docs-memory',
 url: ['https://example.com', 'https://example.com/about'],
 maxPages: 2,
 apiKey: 'your-crawl-key',
 service: 'spider'
});

Key Features

• Seamless Integration: Leverages existing webSearch and webCrawl tools without modification
• Smart Content Formatting: Combines URL and content for better context in search/crawl results
• Automatic Metadata: Adds source tracking (search query, URLs, services used) to all uploads
• Flexible Document Naming: Auto-generation with timestamps or custom prefixes
• Type Safety: Complete TypeScript interfaces with proper exports
• Error Handling: Comprehensive error propagation and validation

Implementation Details

The methods follow the same upload pattern as existing uploadDocs(), using the signed URL approach for efficient content upload. Search and crawl methods return arrays of responses for batch operations, while text upload returns a single response.

Content from search/crawl is formatted as:

URL: https://example.com
Content:
[Page content here...]

Testing & Documentation

• ✅ 5 comprehensive test cases covering all methods and edge cases
• ✅ Complete working examples for each method
• ✅ Full API documentation with parameter descriptions
• ✅ TypeScript compilation and type exports verified

This enhancement addresses the common need to populate memory from various sources and provides a streamlined developer experience for building knowledge bases, research collections, and content repositories.

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.