You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "section9-lab (via GitHub)" <gi...@apache.org> on 2026/07/14 03:49:57 UTC
[PR] [docs][integration] Document Gemini chat model integration [flink-agents]
section9-lab opened a new pull request, #898:
URL: https://github.com/apache/flink-agents/pull/898
Linked issue: #648
### Purpose of change
Document the built-in Google Gemini chat model integration added in #718.
This adds a Gemini section to the chat model provider docs and updates the FAQ native integration support matrix.
### Tests
- `git diff --check`
Docs build was not run locally because Hugo is not installed and the local Docker daemon is not running.
### API
No public API changes.
### Documentation
- [ ] `doc-needed`
- [ ] `doc-not-needed`
- [x] `doc-included`
--
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] [docs][integration] Document Gemini chat model integration [flink-agents]
Posted by "wenjin272 (via GitHub)" <gi...@apache.org>.
wenjin272 commented on code in PR #898:
URL: https://github.com/apache/flink-agents/pull/898#discussion_r3585466817
##########
docs/content/docs/development/chat_models.md:
##########
@@ -643,6 +643,98 @@ Some popular options include:
Model availability depends on your Azure region and subscription. Always check the official Azure OpenAI documentation for regional availability before implementing in production.
{{< /hint >}}
+### Gemini
+
+Google Gemini provides cloud-based chat models through the Gemini Developer API and Vertex AI. The Flink Agents Gemini integration uses the official Google Gen AI SDK and supports text conversations, system instructions, and tool calling.
Review Comment:
This section explicitly presents Vertex AI as a supported backend, but the code comment in `GeminiChatModelConnection` notes:
`“The Vertex path wires the SDK builder flags and is smoke-tested at construction, but a full end-to-end run against Vertex is a follow-up.” `
Has the Vertex AI path been manually verified since then? If not, I suggest clearly marking Vertex AI as experimental and not yet end-to-end verified.
--
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] [docs][integration] Document Gemini chat model integration [flink-agents]
Posted by "section9-lab (via GitHub)" <gi...@apache.org>.
section9-lab commented on code in PR #898:
URL: https://github.com/apache/flink-agents/pull/898#discussion_r3627816311
##########
docs/content/docs/development/chat_models.md:
##########
@@ -643,6 +643,98 @@ Some popular options include:
Model availability depends on your Azure region and subscription. Always check the official Azure OpenAI documentation for regional availability before implementing in production.
{{< /hint >}}
+### Gemini
+
+Google Gemini provides cloud-based chat models through the Gemini Developer API and Vertex AI. The Flink Agents Gemini integration uses the official Google Gen AI SDK and supports text conversations, system instructions, and tool calling.
Review Comment:
Good point. I have not verified the Vertex AI path end to end. I have updated the documentation to clearly mark Vertex AI support as experimental and not yet end-to-end verified.
--
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] [docs][integration] Document Gemini chat model integration [flink-agents]
Posted by "section9-lab (via GitHub)" <gi...@apache.org>.
section9-lab commented on code in PR #898:
URL: https://github.com/apache/flink-agents/pull/898#discussion_r3627816159
##########
docs/content/docs/development/chat_models.md:
##########
@@ -643,6 +643,98 @@ Some popular options include:
Model availability depends on your Azure region and subscription. Always check the official Azure OpenAI documentation for regional availability before implementing in production.
{{< /hint >}}
+### Gemini
+
+Google Gemini provides cloud-based chat models through the Gemini Developer API and Vertex AI. The Flink Agents Gemini integration uses the official Google Gen AI SDK and supports text conversations, system instructions, and tool calling.
+
+{{< hint info >}}
+Gemini is only supported in Java currently. To use Gemini from Python agents, see [Using Cross-Language Providers](#using-cross-language-providers).
+{{< /hint >}}
+
+#### Prerequisites
+
+1. For the Gemini Developer API, create an API key in [Google AI Studio](https://aistudio.google.com/app/apikey)
+2. For Vertex AI, enable Vertex AI in your Google Cloud project and configure Google Cloud credentials
+
+#### GeminiChatModelConnection Parameters
+
+{{< tabs "GeminiChatModelConnection Parameters" >}}
+
+{{< tab "Java" >}}
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `api_key` | String | Required unless `base_url` is set or `vertex_ai` is `true` | Gemini Developer API key |
+| `base_url` | String | None | Custom endpoint, such as a proxy that injects credentials |
+| `model` | String | None | Default model name, used when no model is supplied per setup |
+| `timeout` | int | None | API request timeout in seconds |
+| `vertex_ai` | boolean | `false` | Use Vertex AI instead of the Gemini Developer API |
+| `project` | String | None | Vertex AI project id |
+| `location` | String | None | Vertex AI location |
+
+{{< /tab >}}
+
+{{< /tabs >}}
+
+#### GeminiChatModelSetup Parameters
+
+{{< tabs "GeminiChatModelSetup Parameters" >}}
+
+{{< tab "Java" >}}
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `connection` | String | Required | Reference to connection method name |
+| `model` | String | `"gemini-3.1-pro-preview"` | Name of the chat model to use |
+| `prompt` | Prompt \| String | None | Prompt template or reference to prompt resource |
+| `tools` | List<String> | None | List of tool names available to the model |
+| `temperature` | double | `0.1` | Sampling temperature (0.0 to 2.0) |
+| `max_output_tokens` | long | `1024` | Maximum number of tokens to generate |
+| `additional_kwargs` | Map<String, Object> | `{}` | Additional Gemini parameters (`top_k`, `top_p`, `stop_sequences`) |
+
+{{< /tab >}}
+
+{{< /tabs >}}
+
+#### Usage Example
+
+{{< tabs "Gemini Usage Example" >}}
+
+{{< tab "Java" >}}
+```java
+public class MyAgent extends Agent {
+ @ChatModelConnection
+ public static ResourceDescriptor geminiConnection() {
+ return ResourceDescriptor.Builder.newBuilder(ResourceName.ChatModel.GEMINI_CONNECTION)
+ .addInitialArgument("api_key", System.getenv("GEMINI_API_KEY"))
+ .build();
+ }
+
+ @ChatModelSetup
+ public static ResourceDescriptor geminiChatModel() {
+ return ResourceDescriptor.Builder.newBuilder(ResourceName.ChatModel.GEMINI_SETUP)
+ .addInitialArgument("connection", "geminiConnection")
+ .addInitialArgument("model", "gemini-3.1-pro-preview")
Review Comment:
Confirmed. `gemini-3.1-pro-preview` is currently listed as an available preview model in the [official Gemini API documentation](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview), with no announced shutdown date. Keeping it here is deliberate because it also matches the implementation default. Thanks for checking.
--
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] [docs][integration] Document Gemini chat model integration [flink-agents]
Posted by "section9-lab (via GitHub)" <gi...@apache.org>.
section9-lab commented on code in PR #898:
URL: https://github.com/apache/flink-agents/pull/898#discussion_r3627816159
##########
docs/content/docs/development/chat_models.md:
##########
@@ -643,6 +643,98 @@ Some popular options include:
Model availability depends on your Azure region and subscription. Always check the official Azure OpenAI documentation for regional availability before implementing in production.
{{< /hint >}}
+### Gemini
+
+Google Gemini provides cloud-based chat models through the Gemini Developer API and Vertex AI. The Flink Agents Gemini integration uses the official Google Gen AI SDK and supports text conversations, system instructions, and tool calling.
+
+{{< hint info >}}
+Gemini is only supported in Java currently. To use Gemini from Python agents, see [Using Cross-Language Providers](#using-cross-language-providers).
+{{< /hint >}}
+
+#### Prerequisites
+
+1. For the Gemini Developer API, create an API key in [Google AI Studio](https://aistudio.google.com/app/apikey)
+2. For Vertex AI, enable Vertex AI in your Google Cloud project and configure Google Cloud credentials
+
+#### GeminiChatModelConnection Parameters
+
+{{< tabs "GeminiChatModelConnection Parameters" >}}
+
+{{< tab "Java" >}}
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `api_key` | String | Required unless `base_url` is set or `vertex_ai` is `true` | Gemini Developer API key |
+| `base_url` | String | None | Custom endpoint, such as a proxy that injects credentials |
+| `model` | String | None | Default model name, used when no model is supplied per setup |
+| `timeout` | int | None | API request timeout in seconds |
+| `vertex_ai` | boolean | `false` | Use Vertex AI instead of the Gemini Developer API |
+| `project` | String | None | Vertex AI project id |
+| `location` | String | None | Vertex AI location |
+
+{{< /tab >}}
+
+{{< /tabs >}}
+
+#### GeminiChatModelSetup Parameters
+
+{{< tabs "GeminiChatModelSetup Parameters" >}}
+
+{{< tab "Java" >}}
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `connection` | String | Required | Reference to connection method name |
+| `model` | String | `"gemini-3.1-pro-preview"` | Name of the chat model to use |
+| `prompt` | Prompt \| String | None | Prompt template or reference to prompt resource |
+| `tools` | List<String> | None | List of tool names available to the model |
+| `temperature` | double | `0.1` | Sampling temperature (0.0 to 2.0) |
+| `max_output_tokens` | long | `1024` | Maximum number of tokens to generate |
+| `additional_kwargs` | Map<String, Object> | `{}` | Additional Gemini parameters (`top_k`, `top_p`, `stop_sequences`) |
+
+{{< /tab >}}
+
+{{< /tabs >}}
+
+#### Usage Example
+
+{{< tabs "Gemini Usage Example" >}}
+
+{{< tab "Java" >}}
+```java
+public class MyAgent extends Agent {
+ @ChatModelConnection
+ public static ResourceDescriptor geminiConnection() {
+ return ResourceDescriptor.Builder.newBuilder(ResourceName.ChatModel.GEMINI_CONNECTION)
+ .addInitialArgument("api_key", System.getenv("GEMINI_API_KEY"))
+ .build();
+ }
+
+ @ChatModelSetup
+ public static ResourceDescriptor geminiChatModel() {
+ return ResourceDescriptor.Builder.newBuilder(ResourceName.ChatModel.GEMINI_SETUP)
+ .addInitialArgument("connection", "geminiConnection")
+ .addInitialArgument("model", "gemini-3.1-pro-preview")
Review Comment:
Confirmed. is currently listed as an available preview model in the [official Gemini API documentation](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview), with no announced shutdown date. Keeping it here is deliberate because it also matches the implementation default. Thanks for checking.
##########
docs/content/docs/development/chat_models.md:
##########
@@ -643,6 +643,98 @@ Some popular options include:
Model availability depends on your Azure region and subscription. Always check the official Azure OpenAI documentation for regional availability before implementing in production.
{{< /hint >}}
+### Gemini
+
+Google Gemini provides cloud-based chat models through the Gemini Developer API and Vertex AI. The Flink Agents Gemini integration uses the official Google Gen AI SDK and supports text conversations, system instructions, and tool calling.
Review Comment:
Good point. I have not verified the Vertex AI path end to end. I will update the documentation to clearly mark Vertex AI support as experimental and not yet end-to-end verified.
--
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] [docs][integration] Document Gemini chat model integration [flink-agents]
Posted by "weiqingy (via GitHub)" <gi...@apache.org>.
weiqingy commented on code in PR #898:
URL: https://github.com/apache/flink-agents/pull/898#discussion_r3584893690
##########
docs/content/docs/development/chat_models.md:
##########
@@ -643,6 +643,98 @@ Some popular options include:
Model availability depends on your Azure region and subscription. Always check the official Azure OpenAI documentation for regional availability before implementing in production.
{{< /hint >}}
+### Gemini
+
+Google Gemini provides cloud-based chat models through the Gemini Developer API and Vertex AI. The Flink Agents Gemini integration uses the official Google Gen AI SDK and supports text conversations, system instructions, and tool calling.
+
+{{< hint info >}}
+Gemini is only supported in Java currently. To use Gemini from Python agents, see [Using Cross-Language Providers](#using-cross-language-providers).
+{{< /hint >}}
+
+#### Prerequisites
+
+1. For the Gemini Developer API, create an API key in [Google AI Studio](https://aistudio.google.com/app/apikey)
+2. For Vertex AI, enable Vertex AI in your Google Cloud project and configure Google Cloud credentials
+
+#### GeminiChatModelConnection Parameters
+
+{{< tabs "GeminiChatModelConnection Parameters" >}}
+
+{{< tab "Java" >}}
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `api_key` | String | Required unless `base_url` is set or `vertex_ai` is `true` | Gemini Developer API key |
+| `base_url` | String | None | Custom endpoint, such as a proxy that injects credentials |
+| `model` | String | None | Default model name, used when no model is supplied per setup |
+| `timeout` | int | None | API request timeout in seconds |
+| `vertex_ai` | boolean | `false` | Use Vertex AI instead of the Gemini Developer API |
+| `project` | String | None | Vertex AI project id |
+| `location` | String | None | Vertex AI location |
+
+{{< /tab >}}
+
+{{< /tabs >}}
+
+#### GeminiChatModelSetup Parameters
+
+{{< tabs "GeminiChatModelSetup Parameters" >}}
+
+{{< tab "Java" >}}
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `connection` | String | Required | Reference to connection method name |
+| `model` | String | `"gemini-3.1-pro-preview"` | Name of the chat model to use |
+| `prompt` | Prompt \| String | None | Prompt template or reference to prompt resource |
+| `tools` | List<String> | None | List of tool names available to the model |
+| `temperature` | double | `0.1` | Sampling temperature (0.0 to 2.0) |
+| `max_output_tokens` | long | `1024` | Maximum number of tokens to generate |
+| `additional_kwargs` | Map<String, Object> | `{}` | Additional Gemini parameters (`top_k`, `top_p`, `stop_sequences`) |
+
+{{< /tab >}}
+
+{{< /tabs >}}
+
+#### Usage Example
+
+{{< tabs "Gemini Usage Example" >}}
+
+{{< tab "Java" >}}
+```java
+public class MyAgent extends Agent {
+ @ChatModelConnection
+ public static ResourceDescriptor geminiConnection() {
+ return ResourceDescriptor.Builder.newBuilder(ResourceName.ChatModel.GEMINI_CONNECTION)
+ .addInitialArgument("api_key", System.getenv("GEMINI_API_KEY"))
+ .build();
+ }
+
+ @ChatModelSetup
+ public static ResourceDescriptor geminiChatModel() {
+ return ResourceDescriptor.Builder.newBuilder(ResourceName.ChatModel.GEMINI_SETUP)
+ .addInitialArgument("connection", "geminiConnection")
+ .addInitialArgument("model", "gemini-3.1-pro-preview")
Review Comment:
The example and the table default (line 688) pin `gemini-3.1-pro-preview`, matching the #718 code default. Since docs are the copy-paste surface, worth a quick check it's generally callable? A verbatim paste would hit model-not-found if it isn't GA yet. Not blocking — ignore if deliberate.
Otherwise, LGTM
--
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] [docs][integration] Document Gemini chat model integration [flink-agents]
Posted by "wenjin272 (via GitHub)" <gi...@apache.org>.
wenjin272 merged PR #898:
URL: https://github.com/apache/flink-agents/pull/898
--
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