Skip to content

Commit dd8bc31

Browse files
authored
Add Azure OpenAI embedding provider (#390)
1 parent c5d1e79 commit dd8bc31

File tree

2 files changed

+5
-3
lines changed

2 files changed

+5
-3
lines changed

api-reference/ingest/ingest-dependencies.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -98,7 +98,7 @@ To add support for available embedding libraries, run the following:
9898
| `pip install "unstructured-ingest[embed-vertexai]"` | Google Vertex AI |
9999
| `pip install "unstructured-ingest[embed-voyageai]"` | Voyage AI |
100100
| `pip install "unstructured-ingest[embed-mixedbreadai]"` | Mixedbread |
101-
| `pip install "unstructured-ingest[openai]"` | OpenAI |
101+
| `pip install "unstructured-ingest[openai]"` | OpenAI, Azure OpenAI |
102102
| `pip install "unstructured-ingest[togetherai]"` | together.ai |
103103

104104
For details about the specific dependencies that are installed, see:

snippets/ingest-configuration-shared/embedding-configuration.mdx

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ A common embedding configuration is a critical component that allows for dynamic
1010

1111
* <Icon icon="v"/><Icon icon="1"/>&nbsp;&nbsp;`aws_secret_access_key`: The AWS secret access key to be used for AWS-based embedders, such as Amazon Bedrock.
1212

13-
* <Icon icon="v"/><Icon icon="2"/>&nbsp;&nbsp;`embedding_provider`: The embedding provider to use while doing embedding. Available values include `aws-bedrock`, `huggingface`, `mixedbread-ai`, `octoai`, `openai`, `togetherai`, `vertexai`, and `voyageai`.
13+
* <Icon icon="v"/><Icon icon="2"/>&nbsp;&nbsp;`embedding_provider`: The embedding provider to use while doing embedding. Available values include `aws-bedrock`, `azure-openai`, `huggingface`, `mixedbread-ai`, `octoai`, `openai`, `togetherai`, `vertexai`, and `voyageai`.
1414

1515
* <Icon icon="v"/><Icon icon="2"/>&nbsp;&nbsp;`embedding_api_key`: The API key to use, if one is required to generate the embeddings through an API service, such as OpenAI.
1616

@@ -24,13 +24,15 @@ A common embedding configuration is a critical component that allows for dynamic
2424

2525
* <Icon icon="v"/><Icon icon="1"/>&nbsp;&nbsp;`model_name`: The specific model to use for the embedding provider, if necessary.
2626

27-
* <Icon icon="v"/><Icon icon="1"/>&nbsp;&nbsp;`provider`: The embedding provider to use while doing embedding. Available values include `aws-bedrock`, `huggingface`, `mixedbread-ai`, `octoai`, `openai`, `togetherai`, `vertexai`, and `voyageai`.
27+
* <Icon icon="v"/><Icon icon="1"/>&nbsp;&nbsp;`provider`: The embedding provider to use while doing embedding. Available values include `aws-bedrock`, `azure-openai`, `huggingface`, `mixedbread-ai`, `octoai`, `openai`, `togetherai`, `vertexai`, and `voyageai`.
2828

2929

3030
<Icon icon="v"/><Icon icon="1"/>&nbsp;&nbsp;The default `model_name` values unless otherwise specified are:
3131

3232
* `aws-bedrock`: None
3333

34+
* `azure-openai`: `text-embedding-ada-002`, with 1536 dimensions
35+
3436
* `huggingface`: `sentence-transformers/all-MiniLM-L6-v2`, with 384 dimensions
3537

3638
* `mixedbread-ai`: `mixedbread-ai/mxbai-embed-large-v1`, with 1024 dimensions

0 commit comments

Comments
 (0)