feat: Gemini and Bedrock for AI Proxy

app/_data/docs_nav_gateway_3.8.x.yml

@@ -392,6 +392,16 @@ items:
             url: /hub/kong-inc/ai-proxy/how-to/llm-provider-integration-guides/llama2/
             generate: false
             absolute_url: true
+      - text: AI Platform Integration Guides
+        items:
+          - text: Amazon Bedrock
+            url: /hub/kong-inc/ai-proxy/how-to/ai-and-machine-learning-platform-integration-guides/bedrock/
+            generate: false
+            absolute_url: true
+          - text: Gemini
+            url: /hub/kong-inc/ai-proxy/how-to/ai-and-machine-learning-platform-integration-guides/gemini/
+            generate: false
+            absolute_url: true
       - text: AI Gateway Analytics
         url: /ai-gateway/ai-analytics/
         generate: false

app/_data/tables/support/gateway/third-party.yml

@@ -168,3 +168,7 @@ _third_party:
       - Raw
       - OLLAMA
       - OpenAI
+  bedrock: &bedrock
+    name: Amazon Bedrock
+  gemini: &gemini
+    name: Gemini

app/_data/tables/support/gateway/versions/38.yml

@@ -105,3 +105,5 @@ third-party:
     - *anthropic
     - *mistral
     - *llama2
+    - *bedrock
+    - *gemini

app/_hub/kong-inc/ai-proxy-advanced/how-to/ai-and-machine-learning-platform-integrations/gemini.md

@@ -0,0 +1,62 @@
+---
+nav_title: Gemini
+title: Set up AI Proxy Advanced with Gemini
+---
+
+## Prerequisites
+* [{{site.base_gateway}} is installed and running](/gateway/latest/get-started/)
+* [Create or retrieve an API key](https://ai.google.dev/gemini-api/docs/api-key) on the Google Cloud API Credentials Page to access Google’s AI services
+
+## Configure the AI Proxy Advanced plugin
+
+1. Create a service in {{site.base_gateway}} that will represent the Google Gemini API:
+```sh
+curl -i -X POST http://localhost:8001/services \
+    --data "name=gemini-service" \
+    --data "url=https://generativelanguage.googleapis.com"
+```
+1. Create a route that maps to the service you defined:
+```sh
+curl -i -X POST http://localhost:8001/routes \
+    --data "paths[]=/gemini" \
+    --data "service.id=$(curl -s http://localhost:8001/services/gemini-service | jq -r '.id')"
+```
+1. Use the Kong Admin API to configure the AI Proxy Advanced plugin to route requests to Google Gemini:
+```sh
+curl -i -X POST http://localhost:8001/services/gemini-service/plugins \
+--header "accept: application/json" \
+--header "Content-Type: application/json" \
+--data '
+{
+  "name": "ai-proxy-advanced",
+  "config": {
+    "targets": [
+      {
+        "route_type": "llm/v1/chat",
+        "auth": {
+          "param_name": "key",
+          "param_value": "<GEMINI_API_TOKEN>",
+          "param_location": "query"
+        },
+        "model": {
+          "provider": "gemini",
+          "name": "gemini-1.5-flash"
+        }
+      }
+    ]
+  }
+}
+'
+```
+
+Be sure to replace `GEMINI_API_TOKEN` with your API token.
+
+### Test the configuration
+
+Make an `llm/v1/chat` type request to test your new endpoint:
+
+```sh
+curl -X POST http://localhost:8000/gemini \
+ -H 'Content-Type: application/json' \
+ --data-raw '{ "messages": [ { "role": "system", "content": "You are a mathematician" }, { "role": "user", "content": "What is 1+1?"} ] }'
+```

app/_hub/kong-inc/ai-proxy-advanced/overview/_index.md

@@ -19,6 +19,8 @@ The following table describes which providers and requests the AI Proxy Advanced
 | Mistral (mistral.ai, OpenAI, raw, and OLLAMA formats) | ✅ | ✅ | ✅ |
 | Llama2 (raw, OLLAMA, and OpenAI formats) | ✅ | ✅ | ✅ |
 | Llama3 (OLLAMA and OpenAI formats) | ✅ | ✅ | ✅ |
+| Amazon Bedrock | ✅ | ✅ | ✅ |
+| Gemini | ✅ | ✅ | ✅ |
 
 ## How it works
 
@@ -81,6 +83,11 @@ The plugin's [`config.route_type`](/hub/kong-inc/ai-proxy-advanced/configuration
 | Llama2        | User-defined                                             | `llm/v1/completions` | User-defined           |
 | Mistral       | User-defined                                             | `llm/v1/chat`        | User-defined           |
 | Mistral       | User-defined                                             | `llm/v1/completions` | User-defined           |
+| Amazon Bedrock     | Use the LLM `chat` upstream path                    | `llm/v1/chat`        | [Use the model name for the specific LLM provider](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html)            |
+| Amazon Bedrock     | Use the LLM `completions` upstream path             | `llm/v1/completions` | [Use the model name for the specific LLM provider](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html)             |
+| Gemini     | `llm/v1/chat`                            | `llm/v1/chat`        | `gemini-1.5-flash` or `gemini-1.5-pro`           |
+| Gemini     | `llm/v1/completions`                     | `llm/v1/completions` | `gemini-1.5-flash` or `gemini-1.5-pro`            |
+
 
 The following upstream URL patterns are used:
 
@@ -92,7 +99,8 @@ The following upstream URL patterns are used:
 | Anthropic | `https://api.anthropic.com:443/{route_type_path}`                                                      |
 | Llama2    | As defined in `config.model.options.upstream_url`                                                      |
 | Mistral   | As defined in  `config.model.options.upstream_url`                                                     |
-
+| Amazon Bedrock   | Use the specific LLM upstream URL                                                   |
+| Gemini  | `https://generativelanguage.googleapis.com`                                                     |
 
 {:.important}
 > While only the **Llama2** and **Mistral** models are classed as self-hosted, the target URL can be overridden for any of the supported providers.

app/_hub/kong-inc/ai-proxy/how-to/ai-and-machine-learning-platform-integration-guides/gemini.md

@@ -0,0 +1,46 @@
+---
+nav_title: Gemini
+title: Set up AI Proxy with Gemini
+---
+
+## Prerequisites
+* [{{site.base_gateway}} is installed and running](/gateway/latest/get-started/)
+* [Create or retrieve an API key](https://ai.google.dev/gemini-api/docs/api-key) on the Google Cloud API Credentials Page to access Google’s AI services
+
+## Configure the AI Proxy plugin
+
+1. Create a service in {{site.base_gateway}} that will represent the Google Gemini API:
+```sh
+curl -i -X POST http://localhost:8001/services \
+    --data "name=gemini-service" \
+    --data "url=https://generativelanguage.googleapis.com"
+```
+1. Create a route that maps to the service you defined:
+```sh
+curl -i -X POST http://localhost:8001/routes \
+    --data "paths[]=/gemini" \
+    --data "service.id=$(curl -s http://localhost:8001/services/gemini-service | jq -r '.id')"
+```
+1. Use the Kong Admin API to configure the AI Proxy Plugin to route requests to Google Gemini:
+```sh
+curl -i -X POST http://localhost:8001/services/gemini-service/plugins \
+--data 'name=ai-proxy' \
+--data 'config.auth.param_name=key' \
+--data 'config.auth.param_value=<GEMINI_API_TOKEN>' \
+--data 'config.auth.param_location=query' \
+--data 'config.route_type=llm/v1/chat' \
+--data 'config.model.provider=gemini' \
+--data 'config.model.name=gemini-1.5-flash'
+```
+
+Be sure to replace `GEMINI_API_TOKEN` with your API token.
+
+### Test the configuration
+
+Make an `llm/v1/chat` type request to test your new endpoint:
+
+```sh
+curl -X POST http://localhost:8000/gemini \
+ -H 'Content-Type: application/json' \
+ --data-raw '{ "messages": [ { "role": "system", "content": "You are a mathematician" }, { "role": "user", "content": "What is 1+1?"} ] }'
+```

app/_hub/kong-inc/ai-proxy/overview/_index.md

@@ -29,6 +29,10 @@ The following table describes which providers and requests the AI Proxy plugin s
 | Llama2 (raw, OLLAMA, and OpenAI formats) | ✅ | ✅ | ✅ |
 | Llama3 (OLLAMA and OpenAI formats) | ✅ | ✅ | ✅ |
 {% endif_version %}
+{% if_version gte:3.8.x %}
+| Amazon Bedrock | ✅ | ✅ | ✅ |
+| Gemini | ✅ | ✅ | ✅ |
+{% endif_version %}
 
 ## How it works
 
@@ -77,6 +81,13 @@ The plugin's [`config.route_type`](/hub/kong-inc/ai-proxy/configuration/#config-
 | Mistral       | User-defined                                             | `llm/v1/chat`        | User-defined           |
 | Mistral       | User-defined                                             | `llm/v1/completions` | User-defined           |
 
+{% if_version gte:3.8.x %}
+| Amazon Bedrock     | Use the LLM `chat` upstream path                    | `llm/v1/chat`        | [Use the model name for the specific LLM provider](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html)            |
+| Amazon Bedrock     | Use the LLM `completions` upstream path             | `llm/v1/completions` | [Use the model name for the specific LLM provider](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html)             |
+| Gemini     | `llm/v1/chat`                            | `llm/v1/chat`        | `gemini-1.5-flash` or `gemini-1.5-pro`           |
+| Gemini     | `llm/v1/completions`                     | `llm/v1/completions` | `gemini-1.5-flash` or `gemini-1.5-pro`            |
+{% endif_version %}
+
 The following upstream URL patterns are used:
 
 | Provider  | URL                                                                                                    |
@@ -88,6 +99,10 @@ The following upstream URL patterns are used:
 | Llama2    | As defined in `config.model.options.upstream_url`                                                      |
 | Mistral   | As defined in  `config.model.options.upstream_url`                                                     |
 
+{% if_version gte:3.8.x %}
+| Amazon Bedrock   | Use the specific LLM upstream URL                                                   |
+| Gemini  | https://generativelanguage.googleapis.com                                                     |
+{% endif_version %}
 
 {:.important}
 > While only the **Llama2** and **Mistral** models are classed as self-hosted, the target URL can be overridden for any of the supported providers.