jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Rename streaming to stream to align with OpenAI API (#1332)

Browse Source 
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
This commit is contained in:
XinyaoWa
2025-01-06 13:25:55 +08:00
committed by GitHub
parent 1f29eca288
commit 464e2d3125
53 changed files with 70 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
DocSum/docker_compose/intel/cpu/xeon/README.md
View File

@@ -289,7 +289,7 @@ You will have the following Docker Images:
**summary_type=map_reduce**
Map_reduce mode will split the inputs into multiple chunks, map each document to an individual summary, then consolidate those summaries into a single global summary. `streaming=True` is not allowed here.
Map_reduce mode will split the inputs into multiple chunks, map each document to an individual summary, then consolidate those summaries into a single global summary. `stream=True` is not allowed here.
In this mode, default `chunk_size` is set to be `min(MAX_TOTAL_TOKENS - input.max_tokens - 50, MAX_INPUT_TOKENS)`

2
DocSum/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -280,7 +280,7 @@ You will have the following Docker Images:
**summary_type=map_reduce**
Map_reduce mode will split the inputs into multiple chunks, map each document to an individual summary, then consolidate those summaries into a single global summary. `streaming=True` is not allowed here.
Map_reduce mode will split the inputs into multiple chunks, map each document to an individual summary, then consolidate those summaries into a single global summary. `stream=True` is not allowed here.
In this mode, default `chunk_size` is set to be `min(MAX_TOTAL_TOKENS - input.max_tokens - 50, MAX_INPUT_TOKENS)`

2
DocSum/docsum.py
View File

@@ -231,7 +231,7 @@ class DocSumService:
frequency_penalty=chat_request.frequency_penalty if chat_request.frequency_penalty else 0.0,
presence_penalty=chat_request.presence_penalty if chat_request.presence_penalty else 0.0,
repetition_penalty=chat_request.repetition_penalty if chat_request.repetition_penalty else 1.03,
streaming=stream_opt,
stream=stream_opt,
model=chat_request.model if chat_request.model else None,
language=chat_request.language if chat_request.language else "auto",
summary_type=summary_type,