Elasticsearch 开放式推理 API 添加对 Azure OpenAI 聊天补全的支持

PUT _inference/completion/azure_openai_completion
{
    "service": "azureopenai",
    "service_settings": {
        "resource_name":"<resource-name>",
        "deployment_id": "<deployment-id>",
        "api_version": "2024-02-01",
        "api_key": "<api-key>"
    }
}

{
    "model_id": "azure_openai_completion",
    "task_type": "completion",
    "service": "azureopenai",
    "service_settings": {
        "resource_name": "<resource-name>",
        "deployment_id": "<deployment-id>",
        "api_version": "2024-02-01"
    },
    "task_settings": {}
}

POST _inference/completion/azure_openai_completion
{
    "input": "What is inference in the context of GenAI?"
}

{
    "completion": [
        {
            "result": "In the context of generative AI, inference refers to the process of generating new data based on the patterns, structures, and relationships the AI has learned from the training data. It involves using a model that has been trained on a lot of data to infer or generate new, similar data. For instance, a generative AI model trained on a collection of paintings might infer or generate new, similar paintings. This is the useful part of machine learning where the actual task is performed."
        }
    ]
}

POST _bulk
{ "index" : { "_index" : "questions" } }
{"question": "What is Elasticsearch?"}
{ "index" : { "_index" : "questions" } }
{"question": "What is Kibana?"}
{ "index" : { "_index" : "questions" } }
{"question": "What is Logstash?"}

{
    "errors": false,
    "took": 385,
    "items": [
        {
            "index": {
                "_index": "questions",
                "_id": "4RO6YY8Bv2OsAP2iNusn",
                "_version": 1,
                "result": "created",
                "_shards": {
                    "total": 2,
                    "successful": 1,
                    "failed": 0
                },
                "_seq_no": 0,
                "_primary_term": 1,
                "status": 201
            }
        },
        {
            "index": {
                "_index": "questions",
                "_id": "4hO6YY8Bv2OsAP2iNuso",
                "_version": 1,
                "result": "created",
                "_shards": {
                    "total": 2,
                    "successful": 1,
                    "failed": 0
                },
                "_seq_no": 1,
                "_primary_term": 1,
                "status": 201
            }
        },
        {
            "index": {
                "_index": "questions",
                "_id": "4xO6YY8Bv2OsAP2iNuso",
                "_version": 1,
                "result": "created",
                "_shards": {
                    "total": 2,
                    "successful": 1,
                    "failed": 0
                },
                "_seq_no": 2,
                "_primary_term": 1,
                "status": 201
            }
        }
    ]
}

PUT _ingest/pipeline/question_answering_pipeline

{
    "processors": [
        {
            "script": {
                "source": "ctx.prompt = 'Please answer the following question: ' + ctx.question"
                }
        },
        {
            "inference": {
                "model_id": "azure_openai_completion",
                "input_output": {
                    "input_field": "prompt",
                    "output_field": "answer"
                }
            }
        },
        {
            "remove": {
                "field": "prompt"
            }
        }
    ]
}

POST _reindex

{
  "source": {
    "index": "questions",
    "size": 50
  },
  "dest": {
    "index": "answers",
    "pipeline": "question_answering_pipeline"
  }
}

{
    "took": 10651,
    "timed_out": false,
    "total": 3,
    "updated": 0,
    "created": 3,
    "deleted": 0,
    "batches": 1,
    "version_conflicts": 0,
    "noops": 0,
    "retries": {
        "bulk": 0,
        "search": 0
    },
    "throttled_millis": 0,
    "requests_per_second": -1.0,
    "throttled_until_millis": 0,
    "failures": []
}

POST answers/_search

{
  "query": {
    "match_all": { }
  }
}

{
    "took": 11,
    "timed_out": false,
    "_shards": { ... },
    "hits": {
        "total": { ... },
        "max_score": 1.0,
        "hits": [
            {
                "_index": "answers",
                "_id": "4RO6YY8Bv2OsAP2iNusn",
                "_score": 1.0,
                "_ignored": [
                    "answer.keyword"
                ],
                "_source": {
                    "model_id": "azure_openai_completion",
                    "question": "What is Elasticsearch?",
                    "answer": "Elasticsearch is an open-source, RESTful, distributed search and analytics engine built on Apache Lucene. It can handle a wide variety of data types, including textual, numerical, geospatial, structured, and unstructured data. Elasticsearch is scalable and designed to operate in real-time, making it an ideal choice for use cases such as application search, log and event data analysis, and anomaly detection."
                }
            },
            { ... },
            { ... }
        ]
    }
}