Commit graph

21 commits

Author SHA1 Message Date
sudipnext
b20199a4e3 feat: Integrate Vertex AI and Azure OpenAI support
- Added environment variables for Vertex AI and Azure OpenAI configurations in docker-compose and user configuration models.
- Updated the application logic to handle Vertex and Azure as new LLM providers, including validation and API key management.
- Enhanced the UI components to support model selection and API key input for Vertex and Azure.
- Updated relevant utility functions and constants to accommodate the new providers.
- Ensured proper error handling for configuration requirements specific to Vertex and Azure.
2026-04-30 06:03:39 +05:45
sauravniraula
f76d17314a
feat: integrates llmai instead of using old llm client and tool call handlers 2026-04-23 11:42:15 +05:45
Sudip Parajuli
7f4d6acdd8
Merge branch 'main' into feat/docker-release-electron-sync 2026-04-20 20:56:20 +05:45
sudipnext
a3a6a1acd2 Refactor code structure and remove redundant changes in multiple sections 2026-04-16 13:33:21 +05:45
sudipnext
c7860127f2 feat: add support for optional embedded Ollama and enhance database migration handling
- Updated docker-compose.yml to allow disabling embedded Ollama via environment variable.
- Refactored Dockerfile and Dockerfile.dev for improved dependency management and installation process.
- Enhanced FastAPI migration scripts to handle orphaned Alembic revisions and added new database migration logic.
- Improved error handling in background tasks and Codex authentication endpoints.
- Added support for font file uploads with better validation and extraction of font names.
- Introduced new image search functionality with support for Pexels and Pixabay APIs.
2026-04-15 15:39:35 +05:45
Christopher Quenneville
f2703ec003 feat: add Open WebUI as image generation provider
Add native support for Open WebUI's image generation API as a new
image provider option. Open WebUI exposes an OpenAI-like
/v1/images/generations endpoint but with key differences that
require special handling:

- Response is a bare JSON array instead of {"data": [...]}
- Image URLs are relative paths (e.g. /api/v1/files/.../content)
- File downloads require the same Bearer auth token

The implementation uses raw HTTP calls via aiohttp rather than the
OpenAI SDK to handle these differences. No model parameter is sent
since Open WebUI manages the image model in its own admin settings.

Backend changes:
- New OPEN_WEBUI enum value in ImageProvider
- generate_image_open_webui() method in ImageGenerationService
- Environment getters/setters for OPEN_WEBUI_IMAGE_URL and
  OPEN_WEBUI_IMAGE_API_KEY
- UserConfig model and config loading/saving pipeline updated

Frontend changes:
- New "Open WebUI" option in image provider dropdown
- Settings UI with URL and optional API key fields
- Validation, field mappings, and config persistence

Docker:
- OPEN_WEBUI_IMAGE_URL and OPEN_WEBUI_IMAGE_API_KEY added to all
  docker-compose service definitions

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 12:27:45 -05:00
sudipnext
2d462d8df4 feat: implement database migration on startup and update dependencies for FastAPI 2026-03-08 20:05:44 +05:45
sudipnext
d2e85a8ffa feat: implement Codex OAuth flow and integrate into application
- Added Codex authentication endpoints and logic for OAuth flow.
- Updated Docker configuration to expose port 1455 for Codex callback.
- Enhanced user configuration model to include Codex-related fields.
- Integrated Codex selection into the LLM provider UI.
- Implemented token management and refresh logic for Codex.
- Added utility functions for handling Codex OAuth tokens and state management.
2026-02-24 18:51:35 +05:45
sauravniraula
908bea18b5
feat: adds gpt image 1.5 2025-12-21 01:14:31 +05:45
shiva raj badu
ea8db1bfdd
feat: replace local image provider with ComfyUI configuration in environment variables and user settings 2025-12-18 22:42:53 +05:45
shiva raj badu
e72cea3655
feat: integrate ComfyUI workflow for local image generation 2025-12-17 21:04:32 +05:45
shiva raj badu
c34fb75302
feat: local image provider 2025-12-15 19:12:34 +05:45
sauravniraula
bcf8dabbed
feat: adds option to disable image generation for slides 2025-11-28 00:27:54 +05:45
sauravniraula
3f523f1491
refactor: removes redis service and env variables, fix(fastapi): user config bool env variables issues, parse tool fix for custom llm on tool call structured output 2025-08-09 03:03:13 +05:45
sauravniraula
c599aa15e4
feat: adds options to select between tool calls/json schema and enable disable thinking for custom models 2025-08-04 14:50:55 +05:45
sauravniraula
e542fdf869
feat(fastapi): adds strict support for every schemas, proper models check, refactor 2025-08-01 00:15:03 +05:45
sauravniraula
2150742a54
feat(fastapi): adds a LLMClient wrapper for better control and error handling 2025-07-30 23:31:21 +05:45
sauravniraula
3439b42086
fix(fastapi): changes custom llm url env name 2025-07-26 21:22:04 +05:45
sauravniraula
41a17da47d
chore(fastapi): organizes all env usage in get and set env utilities 2025-07-19 13:00:45 +05:45
sudipnext
21dca979ce feat: add image provider configuration and validation
- Updated LLMConfig interface to include IMAGE_PROVIDER and PIXABAY_API_KEY.
- Enhanced handleSaveLLMConfig to log the saving process and validate IMAGE_PROVIDER.
- Implemented image provider validation logic in hasValidLLMConfig to check for required API keys based on the selected provider.
- Modified start.js to read IMAGE_PROVIDER and PIXABAY_API_KEY from environment variables and include them in the user configuration setup.
2025-07-18 17:52:23 +05:45
sauravniraula
788c8c4042
refactor(fastapi): progress 2025-07-14 18:49:48 +05:45