yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-12-04 10:58:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

clean up docstrings: AzureOpenAIDocumentEmbedder & AzureOpenAITextEmbedder (#8182)

Browse Source 
* clarify docstrings

* Apply suggestions from code review

Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>

---------

Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>
This commit is contained in:
Daria Fokina 2024-08-13 14:17:47 +02:00 committed by GitHub
parent e343f8fbd5
commit 1284ca285b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 48 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
haystack/components/embedders/azure_document_embedder.py
View File

@ -15,9 +15,10 @@ from haystack.utils import Secret, deserialize_secrets_inplace
@component
class AzureOpenAIDocumentEmbedder:
"""
A component for computing Document embeddings using OpenAI models on Azure.
Calculates document embeddings using OpenAI models deployed on Azure.
### Usage example
Usage example:
```python
from haystack import Document
from haystack.components.embedders import AzureOpenAIDocumentEmbedder
@ -52,44 +53,48 @@ class AzureOpenAIDocumentEmbedder:
max_retries: Optional[int] = None,
):
"""
Create an AzureOpenAIDocumentEmbedder component.
Creates an AzureOpenAIDocumentEmbedder component.
:param azure_endpoint:
The endpoint of the deployed model.
The endpoint of the model deployed on Azure.
:param api_version:
The version of the API to use.
:param azure_deployment:
The deployment of the model, usually matches the model name.
The name of the model deployed on Azure. The default model is text-embedding-ada-002.
:param dimensions:
The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3
The number of dimensions of the resulting embeddings. Only supported in text-embedding-3
and later models.
:param api_key:
The API key used for authentication.
The Azure OpenAI API key.
You can set it with an environment variable `AZURE_OPENAI_API_KEY`, or pass with this
parameter during initialization.
:param azure_ad_token:
Microsoft Entra ID token, see Microsoft's official
Microsoft Entra ID token, see Microsoft's
[Entra ID](https://www.microsoft.com/en-us/security/business/identity-access/microsoft-entra-id)
documentation for more information.
Used to be called Azure Active Directory.
documentation for more information. You can set it with an environment variable
`AZURE_OPENAI_AD_TOKEN`, or pass with this parameter during initialization.
Previously called Azure Active Directory.
:param organization:
The Organization ID. See OpenAI's
[production best practices](https://platform.openai.com/docs/guides/production-best-practices/setting-up-your-organization)
Your organization ID. See OpenAI's
[Setting Up Your Organization](https://platform.openai.com/docs/guides/production-best-practices/setting-up-your-organization)
for more information.
:param prefix:
A string to add at the beginning of each text.
:param suffix:
A string to add at the end of each text.
:param batch_size:
Number of Documents to encode at once.
Number of documents to embed at once.
:param progress_bar:
If True shows a progress bar when running.
If `True`, shows a progress bar when running.
:param meta_fields_to_embed:
List of meta fields that will be embedded along with the Document text.
List of metadata fields to embed along with the document text.
:param embedding_separator:
Separator used to concatenate the meta fields to the Document text.
:param timeout: The timeout in seconds to be passed to the underlying `AzureOpenAI` client, if not set it is
inferred from the `OPENAI_TIMEOUT` environment variable or set to 30.
:param max_retries: Maximum retries to establish a connection with AzureOpenAI if it returns an internal error,
if not set it is inferred from the `OPENAI_MAX_RETRIES` environment variable or set to 5.
Separator used to concatenate the metadata fields to the document text.
:param timeout: The timeout for `AzureOpenAI` client calls, in seconds.
If not set, defaults to either the
`OPENAI_TIMEOUT` environment variable, or 30 seconds.
:param max_retries: Maximum number of retries to contact AzureOpenAI after an internal error.
If not set, defaults to either the `OPENAI_MAX_RETRIES` environment variable or to 5 retries.
"""
# if not provided as a parameter, azure_endpoint is read from the env var AZURE_OPENAI_ENDPOINT
azure_endpoint = azure_endpoint or os.environ.get("AZURE_OPENAI_ENDPOINT")
@ -221,14 +226,14 @@ class AzureOpenAIDocumentEmbedder:
@component.output_types(documents=List[Document], meta=Dict[str, Any])
def run(self, documents: List[Document]) -> Dict[str, Any]:
"""
Embed a list of Documents.
Embeds a list of documents.
:param documents:
Documents to embed.
:returns:
A dictionary with the following keys:
- `documents`: Documents with embeddings
- `documents`: A list of documents with embeddings.
- `meta`: Information about the usage of the model.
"""
if not (isinstance(documents, list) and all(isinstance(doc, Document) for doc in documents)):

37
haystack/components/embedders/azure_text_embedder.py
View File

@ -14,9 +14,10 @@ from haystack.utils import Secret, deserialize_secrets_inplace
@component
class AzureOpenAITextEmbedder:
"""
A component for embedding strings using OpenAI models on Azure.
Embeds strings using OpenAI models deployed on Azure.
### Usage example
Usage example:
```python
from haystack.components.embedders import AzureOpenAITextEmbedder
@ -47,32 +48,36 @@ class AzureOpenAITextEmbedder:
suffix: str = "",
):
"""
Create an AzureOpenAITextEmbedder component.
Creates an AzureOpenAITextEmbedder component.
:param azure_endpoint:
The endpoint of the deployed model.
The endpoint of the model deployed on Azure.
:param api_version:
The version of the API to use.
:param azure_deployment:
The deployment of the model, usually matches the model name.
The name of the model deployed on Azure. The default model is text-embedding-ada-002.
:param dimensions:
The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3
and later models.
:param api_key:
The API key used for authentication.
The Azure OpenAI API key.
You can set it with an environment variable `AZURE_OPENAI_API_KEY`, or pass with this
parameter during initialization.
:param azure_ad_token:
Microsoft Entra ID token, see Microsoft's official
Microsoft Entra ID token, see Microsoft's
[Entra ID](https://www.microsoft.com/en-us/security/business/identity-access/microsoft-entra-id)
documentation for more information.
Used to be called Azure Active Directory.
documentation for more information. You can set it with an environment variable
`AZURE_OPENAI_AD_TOKEN`, or pass with this parameter during initialization.
Previously called Azure Active Directory.
:param organization:
The Organization ID. See OpenAI's
[production best practices](https://platform.openai.com/docs/guides/production-best-practices/setting-up-your-organization)
Your organization ID. See OpenAI's
[Setting Up Your Organization](https://platform.openai.com/docs/guides/production-best-practices/setting-up-your-organization)
for more information.
:param timeout: The timeout in seconds to be passed to the underlying `AzureOpenAI` client, if not set it is
inferred from the `OPENAI_TIMEOUT` environment variable or set to 30.
:param max_retries: Maximum retries to establish a connection with AzureOpenAI if it returns an internal error,
if not set it is inferred from the `OPENAI_MAX_RETRIES` environment variable or set to 5.
:param timeout: The timeout for `AzureOpenAI` client calls, in seconds.
If not set, defaults to either the
`OPENAI_TIMEOUT` environment variable, or 30 seconds.
:param max_retries: Maximum number of retries to contact AzureOpenAI after an internal error.
If not set, defaults to either the `OPENAI_MAX_RETRIES` environment variable, or to 5 retries.
:param prefix:
A string to add at the beginning of each text.
:param suffix:
@ -156,7 +161,7 @@ class AzureOpenAITextEmbedder:
@component.output_types(embedding=List[float], meta=Dict[str, Any])
def run(self, text: str):
"""
Embed a single string.
Embeds a single string.
:param text:
Text to embed.