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
Manish Madan
a4507008c1
complete_stream: Stop response streaming ( #2031 )
...
* (feat:pause-stream) generator exit
* (feat:pause-stream) close request
* (feat:pause-stream) finally close; google anthropic
---------
Co-authored-by: GH Action - Upstream Sync <action@github.com >
2025-10-08 20:37:30 +03:00
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
09b9576eef
feat: enhance message and schema cleaning for Google AI integration
2025-09-11 17:54:46 +05:30
Siddhant Rai
896dcf1f9e
feat: add support for structured output and JSON schema validation
2025-08-13 13:29:51 +05:30
Alex
b404162364
fix: fallback to OpenAILLMHandler when no handler class is found
2025-06-20 16:08:40 +01:00
Siddhant Rai
3351f71813
refactor: tool calls sent when pending and after completion
2025-06-11 12:40:32 +05:30
Siddhant Rai
e5b1a71659
refactor: update fallback LLM initialization to use factory method
2025-06-06 17:23:27 +05:30
Siddhant Rai
35f4b13237
refactor: add fallback LLM configuration options to settings
2025-06-06 17:05:15 +05:30
Siddhant Rai
5f5c31cd5b
refactor: enhance LLM fallback handling and streamline method execution
2025-06-06 16:55:57 +05:30
Siddhant Rai
e9530d5ec5
refactor: update env variable names
2025-06-06 15:29:53 +05:30
Siddhant Rai
92c3c707e1
refactor: reorganize LLM handler structure and improve tool call parsing
2025-06-02 12:17:29 +05:30
Pavel
416b776062
redundant f string
2025-05-15 16:57:41 +04:00
Pavel
dbb822f6b0
fix for OPENAI_BASE_URL + ollama can't connect to container
...
- fix for OpenAI trying to use base_url=""
- fix for ollama container error:
`Error code: 404 - {'error': {'message': 'model "MODEL_NAME" not found, try pulling it first', 'type': 'api_error', 'param': None, 'code': None}}`
2025-05-15 13:50:08 +04:00
Alex
481df4d604
fix: enhance error logging with exception info across multiple modules
2025-05-05 13:12:39 +01:00
Alex
df9d432d29
fix: mongo db database name in settings
2025-04-24 17:29:41 +01:00
ManishMadan2882
0a31ddaae6
(feat:storage) use get storage
2025-04-22 01:41:53 +05:30
ManishMadan2882
c50ff6faa3
(feat:fs abstract) googleLLM class
2025-04-18 21:03:28 +05:30
ManishMadan2882
c8efef8f04
(fix:openai) image uplads, use lambda in process_files
2025-04-18 18:27:02 +05:30
ManishMadan2882
5aa51f5f36
(feat:file_abstract) openai attachments comply
2025-04-18 01:27:21 +05:30
ManishMadan2882
335c21c48a
(fix:attachment) dont calculate MIME again
2025-04-17 16:36:40 +05:30
Alex
ad610d2f90
fix: lint ruff
2025-04-14 23:49:40 +01:00
Alex
5b77f3839b
fix: maybe
2025-04-14 20:24:05 +01:00
Alex
231b792452
fix: streaming with tools google and openai halfway
2025-04-14 18:54:40 +01:00
ManishMadan2882
b468e0c164
(fix:generation) attach + tools
2025-04-13 18:33:26 +05:30
ManishMadan2882
dfe6a8d3e3
(feat:attach) simplify the format for files
2025-04-11 01:53:17 +05:30
ManishMadan2882
dd9ea46e58
(feat:attach) strategy specific to google genai
2025-04-10 01:29:01 +05:30
ManishMadan2882
5421bc1386
(feat:attach) extend support for imgs
2025-04-08 15:51:37 +05:30
ManishMadan2882
1f3d1cc73e
(feat:attach) handle unsupported attachments
2025-04-07 20:15:11 +05:30
ManishMadan2882
e4945b41e9
(feat:files) link attachment to openai_api
2025-04-06 15:57:18 +05:30
ManishMadan2882
f9ad4c068a
(feat:attach) fallback strategy to process docs
2025-04-03 03:26:37 +05:30
ManishMadan2882
95e189d1d8
(feat:base/agents) default attachment
2025-04-02 15:29:04 +05:30
Siddhant Rai
f00802dd6b
fix: llm tests failing
2025-03-19 10:25:46 +05:30
Siddhant Rai
ab95d90284
feat: pass decoded_token to llm and retrievers
2025-03-18 23:46:02 +05:30
Nilesh Agarwal
5438bf9754
fix signature for AzureOpenAILLM
2025-03-14 09:52:09 -07:00
Alex
b76e820122
fix: ruff fix
2025-03-13 00:11:50 +00:00
Alex
51eced00aa
fix: openai compatable with llama and gemini
2025-03-13 00:10:13 +00:00
rock.lee
867c375843
add novita provider
2025-03-08 15:45:49 +08:00
Alex
af69bc9d3c
Merge branch 'main' into feat/agent-refactor-and-logging
2025-03-05 16:04:09 -05:00
Siddhant Rai
f88c34a0be
feat: streaming responses with function call
2025-03-05 09:02:55 +05:30
Alex
84cbc1201c
fix: googles update
2025-02-24 22:30:09 +00:00
Siddhant Rai
f35af54e9f
refactor: clean up code and improve UI elements in various components
2025-02-18 13:10:35 +05:30
Siddhant Rai
5cf5bed6a8
feat: enhance tool call handling with structured message cleaning and improved UI display
2025-02-14 00:15:01 +05:30
Siddhant Rai
9319ec5bb2
feat: api tool + fix google ai no parameters error
2025-01-28 09:53:32 +05:30
Alex
c0c60a4875
fix: ruff linting
2025-01-21 09:37:11 +00:00
Siddhant Rai
1086bfe1ba
fix: wrong role in req messages
2025-01-21 07:19:02 +05:30
Siddhant Rai
d441d5763f
fix: decorators + client error
2025-01-20 19:44:14 +05:30
Alex
a741388447
fix: system message
2025-01-19 22:21:50 +00:00
