4 Commits

Author SHA1 Message Date
Alonso Guevara
7bdeaee94a
Create Language Model Providers and Registry methods. Remove fnllm coupling (#1724)
* Base structure

* Add fnllm providers and Mock LLM

* Remove fnllm coupling, introduce llm providers

* Ruff + Tests fix

* Spellcheck

* Semver

* Format

* Default MockChat params

* Fix more tests

* Fix embedding smoke test

* Fix embeddings smoke test

* Fix MockEmbeddingLLM

* Rename LLM to model. Package organization

* Fix prompt tuning

* Oops

* Oops II
2025-02-20 08:56:20 -06:00
Josh Bradley
f14cda2b6d
Improve default llm retry logic to be more optimized (#1701) 2025-02-13 16:56:37 -05:00
Chris Trevino
5ff2d3c76d
Remove graphrag.llm, replace with fnllm (#1315)
* add fnllm; remove llm folder

* remove llm unit tests

* update imports

* update imports

* formatting

* enable autosave

* update mockllm

* update community reports extractor

* move most llm usage to fnllm

* update type issues

* fix unit tests

* type updates

* update dictionary

* semver

* update llm construction, get integration tests working

* load from llmparameters model

* move ruff settings to ruff.toml

* add gitattributes file

* ignore ruff.toml spelling

* update .gitattributes

* update gitignore

* update config construction

* update prompt var usage

* add cache adapter

* use cache adapter in embeddings calls

* update embedding strategy

* add fnllm

* add pytest-dotenv

* fix some verb tests

* get verbtests running

* update ruff.toml for vscode

* enable ruff native server in vscode

* update artifact inspecting code

* remove local-test update

* use string.replace instead of string.format in community reprots etxractor

* bump timeout

* revert ruff.toml, vscode settings for another pr

* revert cspell config

* revert gitignore

* remove json-repair, update fnllm

* use fnllm generic type interfaces

* update load_llm to use target models

* consolidate chat parameters

* add 'extra_attributes' prop to community report response

* formatting

* update fnllm

* formatting

* formatting

* Add defaults to some llm params to avoid null on params hash

* Formatting

---------

Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
Co-authored-by: Josh Bradley <joshbradley@microsoft.com>
2024-12-05 18:07:47 -06:00
Alonso Guevara
81b81cf60b Initial Release 2024-07-01 15:25:30 -06:00