Commit Graph

44 Commits

Author SHA1 Message Date
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
Siddhant Rai
ba49eea23d Refactor agent creation and update logic to improve error handling and default values; enhance logging for better traceability 2025-10-01 13:56:31 +05:30
Alex
56256051d2 fix: chunking 2025-09-24 22:59:53 +01:00
Siddhant Rai
adcdce8d76 fix: handle invalid chunks value in StreamProcessor and ClassicRAG 2025-09-10 22:10:11 +05:30
Siddhant Rai
2f88890c94 feat: add support for multiple sources in agent configuration and update related components 2025-09-08 22:10:08 +05:30
Ankit Matth
07d59b6640 refactor: use list instead of string parsing 2025-08-23 20:25:29 +05:30
Siddhant Rai
bd73fa9ae7 refactor: remove unused abstract method and improve retrievers 2025-08-20 22:25:31 +05:30
Ankit Matth
6f47aa802b added support for multi select sources 2025-08-16 15:19:19 +05:30
Siddhant Rai
dd9d18208d Merge branch 'main' into refactor/llm-handler 2025-06-06 17:36:31 +05:30
Siddhant Rai
e9530d5ec5 refactor: update env variable names 2025-06-06 15:29:53 +05:30
Alex
31baf181a3 fix: default optimisations 2025-06-05 12:21:40 +01:00
Alex
481df4d604 fix: enhance error logging with exception info across multiple modules 2025-05-05 13:12:39 +01:00
Siddhant Rai
ab95d90284 feat: pass decoded_token to llm and retrievers 2025-03-18 23:46:02 +05:30
Siddhant Rai
c6ce4d9374 feat: logging stacks 2025-02-27 19:14:10 +05:30
Siddhant Rai
1f0b779c64 refactor: folder restructure for agent based workflow 2025-02-25 09:03:45 +05:30
Siddhant Rai
6fed84958e feat: agent-retriever workflow + query rephrase 2025-02-24 16:41:57 +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
e209699b19 feat: add tool calls tracking and show in frontend 2025-02-12 21:47:47 +05:30
Alex
6d68b89ea0 fix: history bug on 2nd message 2025-01-26 15:42:47 +00:00
Siddhant Rai
1086bfe1ba fix: wrong role in req messages 2025-01-21 07:19:02 +05:30
Alex
c2a95b5bec lint: fixing index and classc rag 2024-12-20 17:32:58 +00:00
Alex
0a246d3de7 Merge branch 'main' into tool-use 2024-12-20 17:29:41 +00:00
ManishMadan2882
b19c14787e (fix) avoid stringifying list 2024-12-19 17:58:55 +05:30
Siddhant Rai
daa332aa20 fix: python lint errors 2024-12-19 10:06:06 +05:30
ManishMadan2882
9096013e13 (refactor) remove preprocessing in retrieval 2024-12-19 05:20:55 +05:30
Alex
1f649274d1 feat: tooling init 2024-12-05 22:44:40 +00:00
Alex
9bbe7564a9 fix: llamacpp 2024-11-13 11:45:42 +00:00
Alex
78c819f976 fix: history bug 2024-10-31 17:33:09 +00:00
Siddhant Rai
72e68a163c Merge branch 'main' into feat/analytics-and-logs 2024-09-11 17:58:04 +05:30
Alex
90309d5552 feat: user logging api operations level 2024-09-10 01:30:47 +01:00
Alex
44d225e6ca Merge branch 'main' into 1059-migrating-database-to-new-model 2024-09-09 23:55:25 +01:00
Alex
6c0da2ea94 lint: ruff fix 2024-09-08 17:02:48 +01:00
Alex
a353e69648 feat: new vectors structure 2024-09-08 16:59:51 +01:00
Siddhant Rai
28e06fa684 fix: minor ui inconsistencies 2024-09-03 16:11:24 +05:30
Alex
d9309ebc6e feat: better token counter 2024-08-31 17:07:40 +01:00
ManishMadan2882
1eb168be55 vector indexes to be named after mongo _id 2024-08-11 19:33:31 +05:30
Siddhant Rai
91d730a7bc feat: remote sources have clickable links 2024-05-29 19:07:08 +05:30
Siddhant Rai
220d137e66 feat: dropdown to adjust conversational history limits 2024-05-26 23:13:01 +05:30
Siddhant Rai
af5e73c8cb fix: user_api_key capturing 2024-04-16 15:31:11 +05:30
Siddhant Rai
77991896b4 fix: api_key capturing + pytest errors 2024-04-15 22:32:24 +05:30
Alex
8d7a134cb4 lint: ruff 2024-04-09 17:25:08 +01:00
Alex
1e26943c3e Update application files, fix LLM models, and create new retriever class 2024-04-09 15:45:24 +01:00
Alex
391f686173 Update application files and fix LLM models, create new retriever class 2024-04-09 14:02:33 +01:00