Alex
17698ce774
feat: context compression ( #2173 )
...
* feat: context compression
* fix: ruff
2025-11-24 12:44:19 +02:00
Siddhant Rai
3f7de867cc
feat: model registry and capabilities for multi-provider support ( #2158 )
...
* feat: Implement model registry and capabilities for multi-provider support
- Added ModelRegistry to manage available models and their capabilities.
- Introduced ModelProvider enum for different LLM providers.
- Created ModelCapabilities dataclass to define model features.
- Implemented methods to load models based on API keys and settings.
- Added utility functions for model management in model_utils.py.
- Updated settings.py to include provider-specific API keys.
- Refactored LLM classes (Anthropic, OpenAI, Google, etc.) to utilize new model registry.
- Enhanced utility functions to handle token limits and model validation.
- Improved code structure and logging for better maintainability.
* feat: Add model selection feature with API integration and UI component
* feat: Add model selection and default model functionality in agent management
* test: Update assertions and formatting in stream processing tests
* refactor(llm): Standardize model identifier to model_id
* fix tests
---------
Co-authored-by: Alex <a@tushynski.me >
2025-11-14 13:13:19 +02:00
Siddhant Rai
21e5c261ef
feat: template-based prompt rendering with dynamic namespace injection ( #2091 )
...
* feat: template-based prompt rendering with dynamic namespace injection
* refactor: improve template engine initialization with clearer formatting
* refactor: streamline ReActAgent methods and improve content extraction logic
feat: enhance error handling in NamespaceManager and TemplateEngine
fix: update NewAgent component to ensure consistent form data submission
test: modify tests for ReActAgent and prompt renderer to reflect method changes and improve coverage
* feat: tools namespace + three-tier token budget
* refactor: remove unused variable assignment in message building tests
* Enhance prompt customization and tool pre-fetching functionality
* ruff lint fix
* refactor: cleaner error handling and reduce code clutter
---------
Co-authored-by: Alex <a@tushynski.me >
2025-10-31 12:47:44 +00:00
Nihar
f448e4a615
add configurable provider in settings.py and update ElevenLabs Api ( #2065 ) ( #2074 )
2025-10-22 19:07:21 +03:00
Ali Arda Fincan
ce32dd2907
Feat: Agent Token or Request Limiting ( #2041 )
...
* Update routes.py, added token and request limits to create/update agent operations
* added usage limit check to api endpoints
cannot create agents with usage limit right now that will be implemented
* implemented api limiting as either token limiting or request limiting modes
* minor typo & bug fix
2025-10-13 21:32:46 +03:00
Alex
03452ffd9f
feat: add GitHub access token support and fix file content fetching logic ( #2032 )
2025-10-07 16:53:14 +03:00
Siddhant Rai
70183e234a
refactor: break up monolithic routes.py into modular domain structure
2025-10-03 12:30:04 +05:30
ManishMadan2882
5de15c8413
(feat:11Labs) just functional part
2025-10-02 02:39:53 +05:30
ManishMadan2882
2d0e97b66d
(feat:oauth) provider as state, not args
2025-09-25 04:55:25 +05:30
Siddhant Rai
0ff6c6a154
Merge branch 'main' into feat/remote-mcp
2025-09-15 09:53:58 +05:30
Siddhant Rai
641cf5a4c1
feat: skip empty fields in mcp tool call + improve error handling and response
2025-09-11 19:04:10 +05:30
Siddhant Rai
1bf6af6eeb
feat: finalize remote mcp
2025-09-04 15:10:12 +05:30
Siddhant Rai
7c23f43c63
feat: Add MCP Server management functionality
...
- Implemented encryption utility for securely storing sensitive credentials.
- Added MCPServerModal component for managing MCP server configurations.
- Updated AddToolModal to include MCP server management.
- Enhanced localization with new strings for MCP server features.
- Introduced SVG icons for MCP tools in the frontend.
- Created a new settings section for MCP server configurations in the application.
2025-09-03 15:41:59 +05:30
ManishMadan2882
7e2cbdd88c
(feat:connector) redirect url as backend overhead
2025-09-03 09:57:13 +05:30
ManishMadan2882
3b69bea23d
(chore:settings)addefault oath creds
2025-08-21 17:02:23 +05:30
Alex
9281fac898
fix: improve error logging for index creation and add PARSE_IMAGE_REMOTE setting
2025-08-06 10:40:20 +01:00
Alex
b1d8266eef
feat: implement PGVectorStore for PostgreSQL vector storage
2025-08-05 13:54:39 +01:00
Siddhant Rai
76973a4b4c
feat: answer routes re-structure for better maintainability and reuse
2025-07-23 20:07:42 +05:30
Siddhant Rai
a9e4583695
refactor: use DuckDuckGo and Brave as tools instead of retrievers
2025-06-23 09:22:17 +05:30
Siddhant Rai
c35c5e0793
Refactor image upload handling and add URL strategy setting
2025-06-18 21:54:44 +05:30
Siddhant Rai
35f4b13237
refactor: add fallback LLM configuration options to settings
2025-06-06 17:05:15 +05:30
Siddhant Rai
e9530d5ec5
refactor: update env variable names
2025-06-06 15:29:53 +05:30
Alex
df9d432d29
fix: mongo db database name in settings
2025-04-24 17:29:41 +01:00
Alex
3cd9a72495
add storage type to the settings cofig
2025-04-23 23:13:39 +01:00
Siddhant Rai
6583aeff08
feat: update authentication handling and integrate token usage across frontend and backend
2025-03-18 08:29:57 +05:30
Siddhant Rai
4406426515
feat: implement session_jwt and enhance auth
2025-03-17 11:51:30 +05:30
Siddhant Rai
7fd377bdbe
feat: implement JWT authentication and token management in frontend and backend
2025-03-14 17:07:15 +05:30
Siddhant Rai
c6ce4d9374
feat: logging stacks
2025-02-27 19:14:10 +05:30
Siddhant Rai
7b05afab74
refactor: formatting + token limit for gemini-2.0-flash-exp
2025-02-14 00:27:27 +05:30
Alex
132326136a
added gpt-4o-mini model
2024-12-19 18:17:12 +00:00
Alex
312cb9ae70
feat: image parser
2024-11-19 19:06:53 +00:00
Alex
fd8e277530
Merge branch 'main' into feature_n/lancedb
2024-10-19 16:22:39 +01:00
Alex
204b1b1963
fix: add singleton, logging, connection handle
2024-10-15 11:35:37 +01:00
fadingNA
b329ede52a
add redis configuration
2024-10-12 10:46:37 -04:00
akashmangoai
24383997ef
removed cloud based parameter which are not needed
2024-10-11 21:53:29 +05:30
akashAD98
7e75513151
added support for lacedb as vectordb
2024-09-12 18:51:29 +05:30
Alex
2ff8c0b128
Merge branch 'main' into Jackson
2024-09-05 23:43:17 +01:00
Alex
9526ed0258
feat: added easy way to proxy
2024-09-02 19:46:25 +01:00
Jacksonxhx
1c4d7a6ad1
integrated milvus db
2024-07-30 17:44:27 +08:00
Siddhant Rai
220d137e66
feat: dropdown to adjust conversational history limits
2024-05-26 23:13:01 +05:30
Alex
8d7a134cb4
lint: ruff
2024-04-09 17:25:08 +01:00
Alex
e03e185d30
Add Brave Search retriever and update application files
2024-04-09 17:11:09 +01:00
Alex
19494685ba
Update application files, fix LLM models, and create new retriever class
2024-04-09 16:38:42 +01:00
Alex
abf24fe60f
Update FLASK_DEBUG_MODE setting to use value from settings module
2024-04-08 13:15:58 +01:00
Anton Larin
577556678c
Fix model selection at least for openAI LLM_NAME
2024-03-21 10:14:48 +01:00
Anush008
00dfb07b15
chore: revert to faiss default
2024-02-29 09:48:38 +05:30
Anush008
75c0cadb50
feat: Qdrant vector store
2024-02-28 11:49:15 +05:30
Alex
b7927d8d75
Add PremAI LLM implementation
2024-02-13 14:08:55 +00:00
Alex
b45fd58944
Update EMBEDDINGS_NAME in settings.py and test_vector_store.py
2024-01-09 00:34:04 +00:00
Alex
b3149def82
Update EMBEDDINGS_NAME in settings.py
2024-01-09 00:29:02 +00:00
