Commit graph

8 commits

Author SHA1 Message Date
Danny Avila
33834cd484
🧹 feat: Automatic File Cleanup for Mistral OCR Uploads (#8827)
* chore: Handle optional token_endpoint in OAuth metadata discovery

* chore: Simplify permission typing logic in checkAccess function

* feat: Implement `deleteMistralFile` function and integrate file cleanup in `uploadMistralOCR`
2025-08-03 17:11:14 -04:00
Danny Avila
7e37211458
🗝️ refactor: loadServiceKey to Support Stringified JSON and Env Var Renaming (#8317)
* feat: Enhance loadServiceKey to support stringified JSON input

* chore: Update GOOGLE_SERVICE_KEY_FILE_PATH to GOOGLE_SERVICE_KEY_FILE for consistency
2025-07-08 21:07:33 -04:00
Danny Avila
59d00e99f3
🔍 feat: Fetch Google Service Key and Consolidate Key Loading Logic (#8179) 2025-07-01 22:37:29 -04:00
Danny Avila
20100e120b
🔑 feat: Set Google Service Key File Path (#8130) 2025-06-29 17:09:37 -04:00
Danny Avila
3f3cfefc52
🗒️ feat: Add Google Vertex AI Mistral OCR Strategy (#8125)
* Implemented new uploadGoogleVertexMistralOCR function for processing OCR using Google Vertex AI.
* Added vertexMistralOCRStrategy to handle file uploads.
* Updated FileSources and OCRStrategy enums to include vertexai_mistral_ocr.
* Introduced helper functions for JWT creation and Google service account configuration loading.
2025-06-28 13:26:03 -04:00
Danny Avila
d39b99971f
🧠 fix: Agent Title Config & Resource Handling (#8028)
* 🔧 fix: enhance client options handling in AgentClient and set default recursion limit

- Updated the recursion limit to default to 25 if not specified in agentsEConfig.
- Enhanced client options in AgentClient to include model parameters such as apiKey and anthropicApiUrl from agentModelParams.
- Updated requestOptions in the anthropic endpoint to use reverseProxyUrl as anthropicApiUrl.

* Enhance LLM configuration tests with edge case handling

* chore add return type annotation for getCustomEndpointConfig function

* fix: update modelOptions handling to use optional chaining and default to empty object in multiple endpoint initializations

* chore: update @librechat/agents to version 2.4.42

* refactor: streamline agent endpoint configuration and enhance client options handling for title generations

- Introduced a new `getProviderConfig` function to centralize provider configuration logic.
- Updated `AgentClient` to utilize the new provider configuration, improving clarity and maintainability.
- Removed redundant code related to endpoint initialization and model parameter handling.
- Enhanced error logging for missing endpoint configurations.

* fix: add abort handling for image generation and editing in OpenAIImageTools

* ci: enhance getLLMConfig tests to verify fetchOptions and dispatcher properties

* fix: use optional chaining for endpointOption properties in getOptions

* fix: increase title generation timeout from 25s to 45s, pass `endpointOption` to `getOptions`

* fix: update file filtering logic in getToolFilesByIds to ensure text field is properly checked

* fix: add error handling for empty OCR results in uploadMistralOCR and uploadAzureMistralOCR

* fix: enhance error handling in file upload to include 'No OCR result' message

* chore: update error messages in uploadMistralOCR and uploadAzureMistralOCR

* fix: enhance filtering logic in getToolFilesByIds to include context checks for OCR resources to only include files directly attached to agent

---------

Co-authored-by: Matt Burnett <matt.burnett@shopify.com>
2025-06-23 19:44:24 -04:00
Danny Avila
0103b4b08a
🧹 chore: Cleanup base64 Handling for Azure Mistral OCR (#7892)
* 🧹 chore: Remove Comments and Cleanup base64 handling for Azure Mistral OCR

* chore: Remove unnecessary await from MCP instructions formatting in AgentClient

* ci: Update document_url regex in MistralOCR tests to support PDF format
2025-06-13 18:17:25 -04:00
Danny Avila
5f2d1c5dc9
👁️ feat: Azure Mistral OCR Strategy (#7888)
* 👁️ feat: Add Azure Mistral OCR strategy and endpoint integration

This commit introduces a new OCR strategy named 'azure_mistral_ocr', allowing the use of a Mistral OCR endpoint deployed on Azure. The configuration, schemas, and file upload strategies have been updated to support this integration, enabling seamless OCR processing via Azure-hosted Mistral services.

* 🗑️ chore: Clean up .gitignore by removing commented-out uncommon directory name

* chore: remove unused vars

* refactor: Move createAxiosInstance to packages/api/utils and update imports

- Removed the createAxiosInstance function from the config module and relocated it to a new utils module for better organization.
- Updated import paths in relevant files to reflect the new location of createAxiosInstance.
- Added tests for createAxiosInstance to ensure proper functionality and proxy configuration handling.

* chore: move axios helpers to packages/api

- Added logAxiosError function to @librechat/api for centralized error logging.
- Updated imports across various files to use the new logAxiosError function.
- Removed the old axios.js utility file as it is no longer needed.

* chore: Update Jest moduleNameMapper for improved path resolution

- Added a new mapping for '~/' to resolve module paths in Jest configuration, enhancing import handling for the project.

* feat: Implement Mistral OCR API integration in TS

* chore: Update MistralOCR tests based on new imports

* fix: Enhance MistralOCR configuration handling and tests

- Introduced helper functions for resolving configuration values from environment variables or hardcoded settings.
- Updated the uploadMistralOCR and uploadAzureMistralOCR functions to utilize the new configuration resolution logic.
- Improved test cases to ensure correct behavior when mixing environment variables and hardcoded values.
- Mocked file upload and signed URL responses in tests to validate functionality without external dependencies.

* feat: Enhance MistralOCR functionality with improved configuration and error handling

- Introduced helper functions for loading authentication configuration and resolving values from environment variables.
- Updated uploadMistralOCR and uploadAzureMistralOCR functions to utilize the new configuration logic.
- Added utility functions for processing OCR results and creating error messages.
- Improved document type determination and result aggregation for better OCR processing.

* refactor: Reorganize OCR type imports in Mistral CRUD file

- Moved OCRResult, OCRResultPage, and OCRImage imports to a more logical grouping for better readability and maintainability.

* feat: Add file exports to API and create files index

* chore: Update OCR types for enhanced structure and clarity

- Redesigned OCRImage interface to include mandatory fields and improved naming conventions.
- Added PageDimensions interface for better representation of page metrics.
- Updated OCRResultPage to include dimensions and mandatory images array.
- Refined OCRResult to include document annotation and usage information.

* refactor: use TS counterpart of uploadOCR methods

* ci: Update MistralOCR tests to reflect new OCR result structure

* chore: Bump version of @librechat/api to 1.2.3 in package.json and package-lock.json

* chore: Update CONFIG_VERSION to 1.2.8

* chore: remove unused sendEvent function from config module (now imported from '@librechat/api')

* chore: remove MistralOCR service files and tests (now in '@librechat/api')

* ci: update logger import in ModelService tests to use @librechat/data-schemas

---------

Co-authored-by: arthurolivierfortin <arthurolivier.fortin@gmail.com>
2025-06-13 15:14:57 -04:00