Public/kotaemon
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor embeddings and provide vanilla OpenAI-based embeddings (#11)

Browse Source 
* Prepend all Langchain-based embeddings with LC

* Provide vanilla OpenAI embeddings

* Add test for AzureOpenAIEmbeddings and OpenAIEmbeddings

* Fix disallowed empty string

* Use OpenAIEmbeddings in flowsettings

---------

Co-authored-by: ian_Cin <ian@cinnamon.is>
This commit is contained in:
Duc Nguyen (john)
2024-04-09 15:07:59 +07:00
committed by GitHub
parent e75354d410
commit ed10020ea3
2 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
libs/kotaemon/kotaemon/embeddings/openai.py
View File

@@ -59,7 +59,7 @@ class BaseOpenAIEmbeddings(BaseEmbeddings):
input_ = self.prepare_input(text)
client = self.prepare_client(async_version=False)
resp = self.openai_response(
client, input=[_.text for _ in input_], **kwargs
client, input=[_.text if _.text else " " for _ in input_], **kwargs
).dict()
output_ = sorted(resp["data"], key=lambda x: x["index"])
return [
@@ -73,7 +73,7 @@ class BaseOpenAIEmbeddings(BaseEmbeddings):
input_ = self.prepare_input(text)
client = self.prepare_client(async_version=True)
resp = await self.openai_response(
client, input=[_.text for _ in input_], **kwargs
client, input=[_.text if _.text else " " for _ in input_], **kwargs
).dict()
output_ = sorted(resp["data"], key=lambda x: x["index"])
return [