Update default model to `gpt-35-turbo-16k`

Azure-Samples / chat-with-your-data-solution-accelerator

A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.

MIT License

522 stars 274 forks source link

Closes #790

Purpose

Updates default OpenAI deployment to gpt-35-turbo-16k, which supports more tokens for the bigger prompt.

Does this introduce a breaking change?

[ ] Yes
[x] No (The model version is the same, but more tokens are supported)

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix
[x] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

How to Test

Deploy solution
Add docs to knowledge base
Ask question from knowledge base

What to Check

Response received

File	Stmts	Miss	Cover	Missing
TOTAL	2152	833	61%

File

Stmts

Miss

Cover

Missing

TOTAL

2152

833

61%

Tests	Skipped	Failures	Errors	Time
140	0 :zzz:	0 :x:	0 :fire:	7.681s :stopwatch:

Tests

Skipped

Failures

Errors

Time

140

0 :zzz:

0 :x:

0 :fire:

7.681s :stopwatch: