Age | Commit message (Collapse) | Author | |
---|---|---|---|
2024-05-24 | Pylint fixes. | Alexander_Kabui | |
2024-05-24 | Remove kwargs from LLMErrorr Exceptions and update relevant code. | Alexander_Kabui | |
2024-05-24 | Removed status check on get_gnqa function. | Alexander_Kabui | |
2024-05-24 | Check for null and empty data results and update timeout message | Alexander_Kabui | |
2024-05-24 | Pass query as an argument to api_client ask method. | Alexander_Kabui | |
2024-05-24 | Initialize new class attribute self.query for to pass to LLMError. | Alexander_Kabui | |
2024-05-24 | Remove try/block for get_answer/ask methods:Exception already raised | Alexander_Kabui | |
2024-05-24 | Update custom_request to raise LLMError for Exceptions. | Alexander_Kabui | |
2024-05-24 | Remove redundant llm base class exception. | Alexander_Kabui | |
2024-05-22 | Register LLM error in app. | Alexander_Kabui | |
* do refactoring for gn3:llm:errors | |||
2024-05-21 | Remove obsolete functions. | Alexander_Kabui | |
2024-05-17 | Refactor custom request codebase. | Alexander_Kabui | |
2024-05-17 | Timeout code refactoring. | Alexander_Kabui | |
2024-05-16 | Refactor code for http request adapters. | Alexander_Kabui | |
2024-05-16 | Pylint Fixes. | Alexander_Kabui | |
2024-05-16 | Init code refactoring for clients fahamu interface | Alexander_Kabui | |
2024-05-16 | Minor code refactoring related | Alexander_Kabui | |
2024-05-16 | Pep8 formatting gn3:llm:process. | Alexander_Kabui | |
2024-05-16 | Delete function: only useful when training own llm model. | Alexander_Kabui | |
2024-05-16 | Delete response file | Alexander_Kabui | |
* File is obsolete functionality move to process.py file | |||
2024-05-16 | Move Parsing Doc_Ids to process file | Alexander_Kabui | |
* Context: groups related items | |||
2024-05-16 | Update file to use correct import from response file | Alexander_Kabui | |
2024-05-16 | Refactor code for llm:response | Alexander_Kabui | |
2024-05-16 | Remove unused imports for llm.response file | Alexander_Kabui | |
2024-05-16 | Pep8 Cleanup for llms/errors file | Alexander_Kabui | |
2024-05-16 | Code refactoring | Alexander_Kabui | |
* this commit removes ununsed imports and also refactor GenenetworkQAclient Class | |||
2024-05-16 | Pep8 formatting for response file. | Alexander_Kabui | |
2024-04-04 | Rephrase user feedback for Fahamu API in case it takes too long to respond. | Alexander_Kabui | |
2024-03-26 | fetch pubmed file from /gn-meta/lit | Alexander_Kabui | |
2024-03-25 | pep8 formatting | Alexander_Kabui | |
2024-03-25 | fetch tmpdir from current app connfig | Alexander_Kabui | |
2024-03-18 | delete test file | Alexander_Kabui | |
2024-03-18 | fetch pubmed data from tmpdir | Alexander_Kabui | |
2024-03-15 | add pubmed metadata | Alexander_Kabui | |
2024-03-15 | add error handling for invalid tokens | Alexander_Kabui | |
2024-02-14 | Delete trailing space. | Munyoki Kilyungi | |
Signed-off-by: Munyoki Kilyungi <me@bonfacemunyoki.com> | |||
2024-02-14 | raise error for fahamu api 0 task_id | Alexander_Kabui | |
2024-02-12 | pep8 formatting | Alexander_Kabui | |
2024-01-26 | Feature/gn llm caching (#148) | Alexander Kabui | |
* add logic for querying user gnqa search result * add api endpoints for querying users:qnqa-search-terms,gnqa-results | |||
2024-01-17 | fix error message for empty responses | Alexander_Kabui | |
2024-01-17 | Adjust retry parameters and response handling in custom_request | Alexander_Kabui | |
2024-01-17 | Increase timeout to 30s to fix 'Read timed out issue | Alexander_Kabui | |
2024-01-17 | max no of retries for user to fahamu api | Alexander_Kabui | |
2024-01-17 | Feature/gn llm refactoring (#147) | Alexander Kabui | |
* refactor code for processing response from fahamu client * Add tests for gn-llm | |||
2024-01-16 | add api endpoint for rating reference documents (#146) | Alexander Kabui | |
2024-01-08 | fix query formatting and increase no retries | Alexander_Kabui | |
2024-01-08 | add json file for all references | Alexander_Kabui | |
2024-01-08 | Update retry parameters for custom requests to Fahamu AI endpoint. | Munyoki Kilyungi | |
ATM the GN3 times out with the following trace: ``` 2024-01-08 09:33:08 [2024-01-08 09:33:08 +0000] [50] [CRITICAL] WORKER TIMEOUT (pid:1589) ``` * gn3/llms/client.py (GeneNetworkQAClient.custom_request): Update max_retries and retry_delay. Signed-off-by: Munyoki Kilyungi <me@bonfacemunyoki.com> | |||
2024-01-08 | disable process wait | Alexander_Kabui | |
2024-01-05 | http request header fixes | Alexander_Kabui | |