exo/lm-lib
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Introduce reasoning capabilities in chat and text completion

Browse Source 
- Added AbstractCompletionRequest and AbstractCompletionResponse classes to standardize request and response structures.
- Implemented StreamOptions for streaming responses in chat completions.
- Enhanced ChatCompletionClient and TextCompletionClient to support reasoning content in responses.
- Updated ModelProfile to include reasoning effort and summary details.
- Created GptOssPromptStrategy to handle specific prompt formatting and reasoning extraction.
- Modified existing tests to validate reasoning content in completions.
- Updated configuration properties for reasoning settings in local properties files.
This commit is contained in:
extio-de
2025-10-01 19:05:15 +02:00
parent 34c96f0147
commit 514dad1c7f
32 changed files with 582 additions and 392 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/test/resources/local-chatcompletion.properties
View File

@@ -1,7 +1,7 @@
prompts=
tokenEncoding=cl100k_base
maxTokens=2000
maxContextLength=8000
maxTokens=2500
maxContextLength=16000
temperature=0.4
topP=1.0
modelProvider=OAI_CHAT_COMPLETION
@@ -10,3 +10,5 @@ url=http://localhost:5001
apiKey=
cost1MInTokens=0
cost1MOutTokens=0
reasoningEffort=medium
reasoningSummaryDetails=auto

6
src/test/resources/local-completion.properties
View File

@@ -1,7 +1,7 @@
prompts=gemma
prompts=gpt-oss
tokenEncoding=cl100k_base
maxTokens=2000
maxContextLength=8000
maxTokens=2500
maxContextLength=16000
temperature=0.4
topP=1.0
modelProvider=OAI_TEXT_COMPLETION