agentjido / req_llm / e8f08de9a9667270bc40a535ed5371944976da70

Builds Branch Commit Type Ran Committer Via Coverage
e8f08de9a9667270bc40a535ed5371944976da70 main Fix OpenAI o1 model parameter translation (resolves #8) (#11) * Implement provider option translation and enhance error handling - Introduced `translate_options/3` callback in the `ReqLLM.Provider` module to allow providers to modify option keys... push web-flow github
23.06
56683a4cb50c99c9f38265cfa4419f20280ad9f8-PR-11 feature/unique-model-provider-options Enhance OpenAI provider parameter handling - Introduced a new validation function `validate_mutex!/3` in the `ReqLLM.Provider.DSL` module to ensure that conflicting parameters are not used together, improving error handling for provider options. ... Pull #11 mikehostetler github
22.83
6edf88e447e2f58af02cb8ccac89c6bab7d957b9 main Refine API key management with centralized ReqLLM.Key module (#3) * Refactor mix.exs for Dialyzer configuration and dependency management - Removed the plt_file option from Dialyzer configuration for cleaner setup. - Updated the Credo dependency... push web-flow github
22.87
42c3daeadfc9882342891ce47911e7ec0e837625-PR-11 feature/unique-model-provider-options Add translation for OpenAI o3 model parameters - Implemented `translate_options/3` for OpenAI o3 models to rename `max_tokens` to `max_completion_tokens` and drop the unsupported `temperature` parameter. - This enhancement ensures compatibility w... Pull #11 mikehostetler github
22.18
d29c81227e5b780c04e87e27013cc361749ae2d9 main Fix bang methods to return naked values and streamline documentation (#9) * Refactor documentation examples for clarity and consistency - Updated examples in README.md, usage-rules.md, and guides to remove the use of `{:ok, result}` tuples in fa... push web-flow github
21.94
be6ba77dc97e7a4350c2108f53656d816d41d368-PR-3 feature/refined-key-management Refactor API key management and enhance provider implementations - Replaced the `ReqLLM.Key` module with `ReqLLM.Keys` for improved API key retrieval logic, consolidating key fetching with a clear precedence order. - Updated provider modules (`An... Pull #3 mikehostetler github
22.89
1c52a9817920db2c2919c15c389c1d10c8959f7a-PR-11 feature/unique-model-provider-options Remove extra demo scripts to verify Pull #11 mikehostetler github
22.22
ef60c770cd524e7c730619c39e721a0f3c1ea018-PR-11 feature/unique-model-provider-options Fix OpenAI o1 model parameter translation - Add translate_options/3 callback to Provider behavior for model-specific parameter translation - Implement OpenAI o1 model parameter translation: max_tokens → max_completion_tokens and drop temperature ... Pull #11 mikehostetler github
21.16
20c5d904b413fefeff5b27db94af2ff51526bb73-PR-9 bug/api-return-types Fix mix task to work with new bang method patterns - Updated stream_text mix task to handle bang methods returning streams directly - Changed from case pattern matching to try/rescue for error handling - Fixed type spec to include no_return() for... Pull #9 mikehostetler github
21.94
fad21d4ab875c379a3ec366e984610fde1d72512 main Update README.md to reflect method name change for generating embeddings - Changed the example for generating embeddings from `generate_embeddings/2` to `embed_many/2` to align with the updated API method. - This change improves clarity and ensur... push mikehostetler github
21.96