mirror of
https://github.com/LibreChat-AI/librechat.ai.git
synced 2026-03-27 10:48:32 +07:00
888a9f1e8d
- Introduced `context` capability for agents endpoint, enabling file uploads in chat. - Enhanced `fileConfig` with OCR, text parsing, STT separation, and `fileTokenLimit` parameter. - Added `transactions` object structure for token usage tracking. - Included `jinaApiUrl` in `webSearch` configuration for custom Jina instances. - Updated documentation for `fileConfig` to reflect new fields and processing methods.
36 lines
2.5 KiB
Plaintext
36 lines
2.5 KiB
Plaintext
- Added `context` capability for agents endpoint
|
|
- Enables both "Upload as Text" functionality in chat and "File Context" for agents
|
|
- Allows users to upload files and have their content extracted and included directly in the conversation or agent instructions
|
|
- Works with text parsing by default; no external services required
|
|
- Enhanced by the `ocr` capability when OCR service is configured
|
|
- Default enabled in the capabilities list
|
|
- See [Agents Configuration](/docs/configuration/librechat_yaml/object_structure/agents#capabilities) for details
|
|
|
|
- Added OCR, text parsing, and STT separation to `fileConfig`:
|
|
- Added `ocr` configuration to control which file types use OCR processing
|
|
- Added `text` configuration to control which file types use direct text extraction
|
|
- Added `stt` configuration to control which audio file types use Speech-to-Text transcription
|
|
- Added `fileTokenLimit` parameter to control maximum token limits for file text extraction
|
|
- Separate processing paths for visual documents (OCR), text files (native parsing), and audio files (STT)
|
|
- Processing precedence: OCR > STT > text parsing > fallback
|
|
- Default OCR support: images (JPEG, GIF, PNG, WebP, HEIC, HEIF), PDFs, Office documents, EPUB files
|
|
- Default text parsing support: all text MIME types and common programming languages
|
|
- Default STT support: audio formats (MP3, WAV, FLAC, OGG, M4A, WebM, etc.)
|
|
- Text from attached files is truncated to `fileTokenLimit` at runtime just before prompt construction (default: 100000)
|
|
- See [File Config Object Structure](/docs/configuration/librechat_yaml/object_structure/file_config) for details
|
|
|
|
- Added `transactions` object structure
|
|
- Controls whether token usage records are saved to the database
|
|
- Can be configured independently from the balance system
|
|
- Automatically enabled when `balance.enabled` is set to `true`
|
|
- Default value is `true` to ensure token usage is tracked by default
|
|
- Disabling transactions reduces database storage but prevents historical usage analysis
|
|
- See [Transactions Configuration](/docs/configuration/librechat_yaml/object_structure/transactions) for details
|
|
|
|
- Added `jinaApiUrl` to `webSearch` configuration
|
|
- Environment variable name for the Jina API URL
|
|
- Optional field only needed if using a custom Jina instance
|
|
- If not set in .env, users will be prompted to provide it via UI
|
|
- See [Web Search Configuration](/docs/configuration/librechat_yaml/object_structure/web_search#jinaapiurl) for details
|
|
|