add: connector blueprint for azure openai chat model

opensearch-project · Jan 16, 2024 · 420c8f5 · 420c8f5
1 parent 07a54c6
commit 420c8f5
Showing 1 changed file with 208 additions and 0 deletions.
diff --git a/docs/remote_inference_blueprints/azure_openai_connector_chat_blueprint.md b/docs/remote_inference_blueprints/azure_openai_connector_chat_blueprint.md
@@ -0,0 +1,208 @@
+# Azure OpenAI connector Blueprint for Chat Completion:
+
+## 1. Add Azure OpenAI Endpoint to Trusted URLs:
+
+```json
+PUT /_cluster/settings
+{
+    "persistent": {
+        "plugins.ml_commons.trusted_connector_endpoints_regex": [
+            "^https://.*\\.openai\\.azure\\.com/.*$"
+        ]
+    }
+}
+```
+
+## 2. Create Connector for Azure OpenAI Chat Model:
+
+Refer to [Azure OpenAI Service REST API reference - Chat Completion](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions).
+
+If you are using self-managed Opensearch, you should supply OpenAI API key:
+
+
+```json
+POST /_plugins/_ml/connectors/_create
+{
+  "name": "<YOUR CONNECTOR NAME>",
+  "description": "<YOUR CONNECTOR DESCRIPTION>",
+  "version": "<YOUR CONNECTOR VERSION>",
+  "protocol": "http",
+  "parameters": {
+    "endpoint": "<YOUR RESOURCE NAME>.openai.azure.com/",
+    "deploy-name": "<YOUR DEPLOYMENT NAME>",
+    "model": "gpt-4",
+    "api-version": "<YOUR API VERSION>",
+    "temperature": 0.7
+  },
+  "credential": {
+    "openAI_key": "YOUR API KEY"
+  },
+  "actions": [
+    {
+      "action_type": "predict",
+      "method": "POST",
+      "url": "https://${parameters.endpoint}/openai/deployments/${parameters.deploy-name}/chat/completions?api-version=${parameters.api-version}",
+      "headers": {
+        "api-key": "${credential.openAI_key}"
+      },
+      "request_body": "{ \"messages\": ${parameters.messages}, \"temperature\": ${parameters.temperature} }"
+    }
+  ]
+}
+```
+
+### Sample response:
+```json
+{
+  "connector_id": "EapnEY0BpYxvPx3Hxpmp"
+}
+```
+
+## 3. Create model group:
+
+```json
+POST /_plugins/_ml/model_groups/_register
+{
+    "name": "remote_model_group",
+    "description": "This is an example description"
+}
+```
+
+### Sample response
+```json
+{
+  "model_group_id": "YyvcbYsBjU568JRbdHqv",
+  "status": "CREATED"
+}
+```
+
+## 4. Register model to model group & deploy model:
+
+```json
+POST /_plugins/_ml/models/_register
+{
+    "name": "azure-openAI-gpt-4",
+    "function_name": "remote",
+    "model_group_id": "YyvcbYsBjU568JRbdHqv",
+    "description": "Azure OpenAI GPT 4",
+    "connector_id": "EapnEY0BpYxvPx3Hxpmp"
+}
+```
+
+### Sample response
+```json
+{
+  "task_id": "E6ppEY0BpYxvPx3HZZkL",
+  "status": "CREATED",
+  "model_id": "FKppEY0BpYxvPx3HZZk0"
+}
+```
+
+Check if the task is completed
+```
+GET /_plugins/_ml/tasks/E6ppEY0BpYxvPx3HZZkL
+```
+
+When model registration is completed, deploy it
+```
+POST /_plugins/_ml/models/FKppEY0BpYxvPx3HZZk0/_deploy
+```
+
+## 5. Test model
+```json
+POST /_plugins/_ml/models/FKppEY0BpYxvPx3HZZk0/_predict
+{
+  "parameters": {
+    "messages": [
+      {
+        "role": "system",
+        "content": "You are a helpful assistant."
+      },
+      {
+        "role": "user",
+        "content": "Hello!"
+      }
+    ]
+  }
+}
+```
+
+### Sample response
+
+```json
+{
+  "inference_results": [
+    {
+      "output": [
+        {
+          "name": "response",
+          "dataAsMap": {
+            "id": "chatcmpl-8hZDlKJIaFLrC2sGTI2EYBiHQUhdI",
+            "object": "chat.completion",
+            "created": 1705394185,
+            "model": "gpt-35-turbo",
+            "prompt_filter_results": [
+              {
+                "prompt_index": 0,
+                "content_filter_results": {
+                  "hate": {
+                    "filtered": false,
+                    "severity": "safe"
+                  },
+                  "self_harm": {
+                    "filtered": false,
+                    "severity": "safe"
+                  },
+                  "sexual": {
+                    "filtered": false,
+                    "severity": "safe"
+                  },
+                  "violence": {
+                    "filtered": false,
+                    "severity": "safe"
+                  }
+                }
+              }
+            ],
+            "choices": [
+              {
+                "finish_reason": "stop",
+                "index": 0,
+                "message": {
+                  "role": "assistant",
+                  "content": "Hello! How can I assist you today?"
+                },
+                "content_filter_results": {
+                  "hate": {
+                    "filtered": false,
+                    "severity": "safe"
+                  },
+                  "self_harm": {
+                    "filtered": false,
+                    "severity": "safe"
+                  },
+                  "sexual": {
+                    "filtered": false,
+                    "severity": "safe"
+                  },
+                  "violence": {
+                    "filtered": false,
+                    "severity": "safe"
+                  }
+                }
+              }
+            ],
+            "usage": {
+              "prompt_tokens": 19,
+              "completion_tokens": 9,
+              "total_tokens": 28
+            }
+          }
+        }
+      ],
+      "status_code": 200
+    }
+  ]
+}
+```
+