feat: Amazon Bedrock Embedding doc

Author: chezou

docs/embeddings.md

@@ -20,6 +20,7 @@ Chroma provides lightweight wrappers around popular embedding providers, making
 | [Instructor](/embeddings/instructor) | ✅  | ➖ |
 | [Hugging Face Embedding Server](/embeddings/hugging-face-embedding-server) | ✅  | ✅ |
 | [Jina AI](/embeddings/jinaai) | ✅  | ✅ |
+| [Amazon Bedrock](/embeddings/amazon-bedrock) | ✅  | ➖ |
 
 We welcome pull requests to add new Embedding Functions to the community.
 

docs/embeddings/amazon-bedrock.md

@@ -0,0 +1,29 @@
+---
+---
+
+# Amazon Bedrock
+
+Chroma provides a convinient wrapper for [Amazon Bedrock](https://aws.amazon.com/bedrock/) embedding API. This embedding function runs remotely on Amazon's servers, and requires an Amazon client session.
+
+To use Amazon Bedrock embedding API, you must have `boto3` Python package installed and create an instance of `boto3.Session` with your AWS credentials. To use:
+
+```python
+import boto3
+import chromadb.utils.embedding_functions as embedding_functions
+
+session = boto3.Session(
+    aws_access_key_id=aws_access_key_id,
+    aws_secret_access_key=aws_secret_access_key,
+    region_name=region_name,
+)
+bedrock = embedding_functions.AmazonBedrockEmbeddingFunction(session=session)
+bedrock(["document1","document2"])
+```
+
+By default, the embedding function uses the `amazon.titan-embed-text-v1` for the model, but you can specify a different model name with `model_name` parameter. For example:
+
+```python
+bedrock = embedding_functions.AmazonBedrockEmbeddingFunction(
+    session=session, model_name="cohere.embed-multilingual-v3")
+bedrock(["こんにちは", "你们好"])
+```

sidebars.js

@@ -93,6 +93,7 @@ const sidebars = {
         'embeddings/instructor',
         'embeddings/hugging-face-embedding-server',
         'embeddings/jinaai',
+        'embeddings/amazon-bedrock',
       ],
     },
   ],