You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "avichaym (via GitHub)" <gi...@apache.org> on 2026/05/14 14:45:16 UTC
[PR] [Doc] Add documentation for Amazon Bedrock, Amazon OpenSearch, and Amazon S3 Vectors integrations [flink-agents]
avichaym opened a new pull request, #680:
URL: https://github.com/apache/flink-agents/pull/680
fixes #676
Depends on #679 for constant names - please merge that first
Adds per-provider doc sections for the AWS integrations from #533 and #534:
chat_models.md - Bedrock (Converse API, SigV4 auth, tool calling, model IDs)
embedding_models.md - Bedrock (Titan Embeddings V2, configurable dimensions)
vector_stores.md - OpenSearch (Serverless + domains, IAM/basic auth) and S3 Vectors
Follows the same structure as Anthropic/Ollama/OpenAI/Elasticsearch sections. Hugo-rendered and verified locally.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscribe@flink.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Doc] Add documentation for Amazon Bedrock, Amazon OpenSearch, and Amazon S3 Vectors integrations [flink-agents]
Posted by "xintongsong (via GitHub)" <gi...@apache.org>.
xintongsong merged PR #680:
URL: https://github.com/apache/flink-agents/pull/680
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscribe@flink.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Doc] Add documentation for Amazon Bedrock, Amazon OpenSearch, and Amazon S3 Vectors integrations [flink-agents]
Posted by "xintongsong (via GitHub)" <gi...@apache.org>.
xintongsong commented on code in PR #680:
URL: https://github.com/apache/flink-agents/pull/680#discussion_r3297930919
##########
docs/content/docs/development/vector_stores.md:
##########
@@ -642,6 +642,204 @@ public static ResourceDescriptor vectorStore() {
{{< /tabs >}}
+### Amazon OpenSearch
+
+[Amazon OpenSearch](https://docs.aws.amazon.com/opensearch-service/latest/developerguide/) is a managed vector search service available in two flavors: OpenSearch Service (provisioned domains) and OpenSearch Serverless (AOSS). The Flink Agents integration supports both via a single `service_type` parameter, with IAM (SigV4) or basic authentication.
+
+{{< hint info >}}
+Amazon OpenSearch is only supported in Java currently. To use Amazon OpenSearch from Python agents, see [Using Cross-Language Providers](#using-cross-language-providers).
+{{< /hint >}}
+
+{{< hint info >}}
+Amazon OpenSearch implements `CollectionManageableVectorStore`, enabling [Long-Term Memory]({{< ref "docs/development/memory/long_term_memory" >}}) support. Collections map to OpenSearch indices, with collection metadata stored in a dedicated `flink_agents_collection_metadata` index.
Review Comment:
This seems inaccurate? I could not find `flink_agents_collection_Metadata` in the codes, and the JavaDoc says "this implementation does not persist any collection-level metadata".
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscribe@flink.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Doc] Add documentation for Amazon Bedrock, Amazon OpenSearch, and Amazon S3 Vectors integrations [flink-agents]
Posted by "avichaym (via GitHub)" <gi...@apache.org>.
avichaym commented on code in PR #680:
URL: https://github.com/apache/flink-agents/pull/680#discussion_r3298177543
##########
docs/content/docs/development/vector_stores.md:
##########
@@ -642,6 +642,204 @@ public static ResourceDescriptor vectorStore() {
{{< /tabs >}}
+### Amazon OpenSearch
+
+[Amazon OpenSearch](https://docs.aws.amazon.com/opensearch-service/latest/developerguide/) is a managed vector search service available in two flavors: OpenSearch Service (provisioned domains) and OpenSearch Serverless (AOSS). The Flink Agents integration supports both via a single `service_type` parameter, with IAM (SigV4) or basic authentication.
+
+{{< hint info >}}
+Amazon OpenSearch is only supported in Java currently. To use Amazon OpenSearch from Python agents, see [Using Cross-Language Providers](#using-cross-language-providers).
+{{< /hint >}}
+
+{{< hint info >}}
+Amazon OpenSearch implements `CollectionManageableVectorStore`, enabling [Long-Term Memory]({{< ref "docs/development/memory/long_term_memory" >}}) support. Collections map to OpenSearch indices, with collection metadata stored in a dedicated `flink_agents_collection_metadata` index.
Review Comment:
Thanks @xintongsong for the review. All three asks addressed :
* Fixed the inaccurate flink_agents_collection_metadata claim - replaced with text matching the Javadoc (collection metadata is ignored, OpenSearch indices don't natively support arbitrary metadata).
* Moved Amazon Bedrock / Amazon OpenSearch / Amazon S3 Vectors to alphabetical position in each file (they now sort first).
*Rebased onto latest main, dropping the stale commit.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscribe@flink.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org