30 Commits

Author SHA1 Message Date
perf3ct
224cae6db2
fix(unit): resolve type errors 2025-06-08 21:03:07 +00:00
perf3ct
a8faf5d699
fix(unit): still working on getting the LLM unit tests to pass... 2025-06-08 18:13:27 +00:00
perf3ct
e011c56715
fix(unit): no more type errors hopefully 2025-06-08 16:33:26 +00:00
Jon Fuller
d7abd3a8ed
Merge branch 'develop' into feat/llm-unit-tests 2025-06-08 08:49:08 -07:00
perf3ct
414781936b
fix(llm): always fetch the user's selected model 2025-06-07 23:36:53 +00:00
perf3ct
7f9ad04b57
feat(llm): create unit tests for LLM services 2025-06-07 21:03:54 +00:00
perf3ct
b0d804da08
fix(llm): remove the vectorSearch stage from the pipeline 2025-06-07 18:57:08 +00:00
perf3ct
4550c12c6e
feat(llm): remove everything to do with embeddings, part 3 2025-06-07 18:30:46 +00:00
perf3ct
44a45780b7
feat(llm): remove everything to do with embeddings 2025-06-07 18:11:12 +00:00
perf3ct
cb3844e627
fix(llm): fix duplicated text when streaming responses 2025-06-07 00:27:56 +00:00
perf3ct
c26b74495c
feat(llm): remove LLM deprecated functions 2025-06-05 22:34:20 +00:00
perf3ct
bb8a374ab8
feat(llm): transition from initializing LLM providers, to creating them on demand 2025-06-05 19:27:45 +00:00
perf3ct
fe15a0378a
fix(llm): have the model_selection_stage use the instance of the aiServiceManager 2025-06-04 20:23:06 +00:00
perf3ct
a20e36f4ee
feat(llm): change from using precedence list to using a sing specified provider for either chat and/or embeddings 2025-06-04 20:13:13 +00:00
perf3ct
d4d55b20a8
fix(llm): get rid of a lot of log.info() statements that were spammy 2025-06-03 03:00:15 +00:00
perf3ct
ce7c4a31a1
refactor(llm): enhance configuration handling to avoid default assumptions and improve error handling 2025-06-02 21:43:36 +00:00
perf3ct
45175b6af3
refactor(llm): integrate new configuration system for provider management and model selection 2025-06-02 21:36:19 +00:00
perf3ct
dcab4caee3
feat(llm): redo chat storage, part 3 2025-06-02 15:12:08 +00:00
perf3ct
a7906d6b99
refactor(llm): improve search tools error handling and parameter validation with clearer guidance 2025-05-30 00:23:18 +00:00
perf3ct
910c5039f4
feat(llm): add LLM guidance system for failed tool executions and validations 2025-05-30 00:15:40 +00:00
perf3ct
f04e56137b
refactor(llm): improve type safety in tool calling stage and simplify tool call handling 2025-05-29 22:05:38 +00:00
perf3ct
7c63652105
feat(llm): improve type safety and error handling in tool call transformations 2025-05-29 22:03:23 +00:00
perf3ct
87859aec1c
fix(llm): reduce the use of "any" in the tool_calling_stage and update prompt for tool calling 2025-05-29 21:15:05 +00:00
perf3ct
ba59d6b3c1
feat(llm): reduce the use of "any" in the tool calling stage 2025-05-29 21:07:12 +00:00
perf3ct
511d2c5e96
feat(llm): add empty result handling and parameter adjustment suggestions for tool execution 2025-05-29 21:04:06 +00:00
Elian Doran
ba7c93967e
chore(server): fix some type errors 2025-05-28 19:03:53 +03:00
Elian Doran
6e35806340
chore(monorepo/server): fix build errors due to wrong imports 2025-04-22 19:21:19 +03:00
Elian Doran
b2af043110
chore(nx/server): move source code 2025-04-22 17:16:41 +03:00
Elian Doran
62dbcc0a2e
chore(nx): move all monorepo-style in subfolder for processing 2025-04-22 10:06:06 +03:00
Elian Doran
5058891af8
chore(monorepo/server): move server-side source code 2025-04-18 12:09:56 +03:00