# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for Elasticsearch Request & Response Specification Inference API
  version: 1.0.0
extends: openapi/elk-stack-inference-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-09-26'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 48
- target: $.paths['/_inference/chat_completion/{inference_id}/_stream'].post
  update:
    x-apievangelist-phrasing:
      intent: Stream a chat completion from an inference endpoint
      effect: write
      questions:
      - Can I stream a multi-turn chat conversation through an Elasticsearch chat_completion endpoint?
      - Does the streaming chat API let me pass tools and a tool_choice to the model?
      - What controls do I get over temperature and max completion tokens when streaming a chat reply?
      instructions:
      - text: 'Stream a chat reply from chat_completion endpoint {inference_id} for these messages: {messages}.'
        slots:
          inference_id: path.inference_id
          messages: requestBody.messages
      - text: Send {messages} to chat endpoint {inference_id} with temperature {temperature} and stream the answer back.
        slots:
          messages: requestBody.messages
          inference_id: path.inference_id
          temperature: requestBody.temperature
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/completion/{inference_id}'].post
  update:
    x-apievangelist-phrasing:
      intent: Get a text completion from an inference endpoint
      effect: write
      questions:
      - How do I get a non-streaming text completion from a completion inference endpoint?
      - Can I send a prompt to a completion endpoint and get the whole answer back in one response?
      instructions:
      - text: Complete the prompt {input} using completion endpoint {inference_id} and return the full response.
        slots:
          input: requestBody.input
          inference_id: path.inference_id
      - text: Run a one-shot completion on {inference_id} for {input}.
        slots:
          inference_id: path.inference_id
          input: requestBody.input
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{inference_id}'].get
  update:
    x-apievangelist-phrasing:
      intent: Look up an inference endpoint by ID
      effect: read
      questions:
      - What service and settings is a given inference endpoint configured with?
      - Can I look up one inference endpoint by its ID without knowing its task type?
      instructions:
      - text: Show me the configuration of inference endpoint {inference_id}.
        slots:
          inference_id: path.inference_id
      - text: Look up inference endpoint {inference_id} by ID alone.
        slots:
          inference_id: path.inference_id
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an inference endpoint without a task type
      effect: write
      questions:
      - Can I create an inference endpoint just by ID, letting the service determine the task type?
      - What do I need to supply in service and service_settings to register a generic inference endpoint?
      instructions:
      - text: Create inference endpoint {inference_id} using service {service} with settings {service_settings}, no task type in the path.
        slots:
          inference_id: path.inference_id
          service: requestBody.service
          service_settings: requestBody.service_settings
      - text: Register a new inference endpoint named {inference_id} on the {service} service.
        slots:
          inference_id: path.inference_id
          service: requestBody.service
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{inference_id}'].post
  update:
    x-apievangelist-phrasing:
      intent: Run inference against an endpoint by ID
      effect: write
      questions:
      - Can I send input to an inference endpoint by ID and let it perform whatever task it was configured for?
      - Which input do I pass to run a generic inference call when I don't want to name the task type?
      instructions:
      - text: Run inference endpoint {inference_id} on the input {input}.
        slots:
          inference_id: path.inference_id
          input: requestBody.input
      - text: Call {inference_id} with {input} using its configured task, no task type given.
        slots:
          inference_id: path.inference_id
          input: requestBody.input
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{inference_id}'].delete
  update:
    x-apievangelist-phrasing:
      intent: Delete an inference endpoint by ID
      effect: destructive
      questions:
      - How do I remove an inference endpoint I no longer need?
      - Can I do a dry run to see which ingest pipelines still reference an inference endpoint before deleting it?
      instructions:
      - text: Delete inference endpoint {inference_id}.
        slots:
          inference_id: path.inference_id
      - text: Dry-run deleting inference endpoint {inference_id} to see what references it.
        slots:
          inference_id: path.inference_id
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{inference_id}'].get
  update:
    x-apievangelist-phrasing:
      intent: Look up an inference endpoint by task type and ID
      effect: read
      questions:
      - Can I fetch an inference endpoint scoped to a specific task type like text_embedding?
      - What configuration does my rerank endpoint have when I look it up under its task type?
      instructions:
      - text: Get the {task_type} inference endpoint {inference_id}.
        slots:
          task_type: path.task_type
          inference_id: path.inference_id
      - text: Show the settings for {inference_id} under task type {task_type}.
        slots:
          inference_id: path.inference_id
          task_type: path.task_type
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an inference endpoint for a task type
      effect: write
      questions:
      - How do I create an inference endpoint for a specific task type such as sparse_embedding or completion?
      - Can I set chunking settings when creating an inference endpoint for a given task type?
      instructions:
      - text: Create a {task_type} inference endpoint {inference_id} on service {service}.
        slots:
          task_type: path.task_type
          inference_id: path.inference_id
          service: requestBody.service
      - text: Set up {inference_id} for task type {task_type} with service settings {service_settings}.
        slots:
          inference_id: path.inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{inference_id}'].post
  update:
    x-apievangelist-phrasing:
      intent: Run inference for a given task type
      effect: write
      questions:
      - Can I run inference while naming the task type explicitly in the request path?
      - What happens if I call an endpoint with a task type it wasn't created for?
      instructions:
      - text: Run {task_type} inference on endpoint {inference_id} with input {input}.
        slots:
          task_type: path.task_type
          inference_id: path.inference_id
          input: requestBody.input
      - text: Use the {task_type} endpoint {inference_id} to process {input}.
        slots:
          task_type: path.task_type
          inference_id: path.inference_id
          input: requestBody.input
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{inference_id}'].delete
  update:
    x-apievangelist-phrasing:
      intent: Delete an inference endpoint of a task type
      effect: destructive
      questions:
      - Can I delete an inference endpoint by naming both its task type and ID?
      - Is there a force option to delete a task-typed inference endpoint that pipelines still use?
      instructions:
      - text: Delete the {task_type} inference endpoint {inference_id}.
        slots:
          task_type: path.task_type
          inference_id: path.inference_id
      - text: Force-delete {inference_id} under task type {task_type} even if it is referenced.
        slots:
          inference_id: path.inference_id
          task_type: path.task_type
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/_region_policy'].get
  update:
    x-apievangelist-phrasing:
      intent: Get the inference region policy
      effect: read
      questions:
      - Which geographic regions is inference currently restricted to on my cluster?
      - Is there a region policy set for inference right now?
      instructions:
      - text: Show me the current inference region policy.
      - text: Check which regions inference is allowed to run in.
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/_region_policy'].put
  update:
    x-apievangelist-phrasing:
      intent: Set the inference region policy
      effect: write
      questions:
      - How do I restrict inference to certain cloud regions or geographic areas?
      - Can I change the allowed inference regions after a policy already exists?
      instructions:
      - text: Restrict inference to the regions in {region_policy}.
        slots:
          region_policy: requestBody.region_policy
      - text: Update the inference region policy to {region_policy}, forcing the change.
        slots:
          region_policy: requestBody.region_policy
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/_region_policy'].delete
  update:
    x-apievangelist-phrasing:
      intent: Remove the inference region policy
      effect: destructive
      questions:
      - How can I lift the geographic restriction on where inference runs?
      - What removes the inference region policy entirely?
      instructions:
      - text: Delete the inference region policy.
      - text: Remove all regional restrictions on inference.
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/embedding/{inference_id}'].post
  update:
    x-apievangelist-phrasing:
      intent: Generate dense embeddings for input
      effect: write
      questions:
      - Can I get dense vector embeddings from an embedding task endpoint?
      - Does the dense embedding call accept an input_type to mark the text as a query or a document?
      instructions:
      - text: Generate dense embeddings for {input} using embedding endpoint {inference_id}.
        slots:
          input: requestBody.input
          inference_id: path.inference_id
      - text: Embed {input} as dense vectors with {inference_id}, input type {input_type}.
        slots:
          input: requestBody.input
          inference_id: path.inference_id
          input_type: requestBody.input_type
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference'].get
  update:
    x-apievangelist-phrasing:
      intent: List all inference endpoints
      effect: read
      questions:
      - What inference endpoints exist on my cluster across every task type?
      - Can I see every inference endpoint, including the preconfigured ELSER and E5 ones?
      instructions:
      - text: List all my inference endpoints.
      - text: Show every inference endpoint on the cluster regardless of task type.
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/_all'].get
  update:
    x-apievangelist-phrasing:
      intent: List inference endpoints for one task type
      effect: read
      questions:
      - Which inference endpoints do I have for text_embedding?
      - Can I list only the rerank endpoints on my cluster?
      instructions:
      - text: List all {task_type} inference endpoints.
        slots:
          task_type: path.task_type
      - text: Show every endpoint configured for task type {task_type}.
        slots:
          task_type: path.task_type
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{ai21_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an AI21 inference endpoint
      effect: write
      questions:
      - How do I connect Elasticsearch to AI21 models for completion or chat?
      - What service settings does an ai21 inference endpoint need?
      instructions:
      - text: Create an AI21 {task_type} inference endpoint named {ai21_inference_id}.
        slots:
          task_type: path.task_type
          ai21_inference_id: path.ai21_inference_id
      - text: Set up AI21 endpoint {ai21_inference_id} for {task_type} with settings {service_settings}.
        slots:
          ai21_inference_id: path.ai21_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{alibabacloud_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an AlibabaCloud AI Search inference endpoint
      effect: write
      questions:
      - Can I use AlibabaCloud AI Search models for embeddings or reranking in Elasticsearch?
      - What's needed to register an alibabacloud-ai-search inference endpoint?
      instructions:
      - text: Create an AlibabaCloud AI Search {task_type} endpoint {alibabacloud_inference_id}.
        slots:
          task_type: path.task_type
          alibabacloud_inference_id: path.alibabacloud_inference_id
      - text: Register AlibabaCloud AI Search endpoint {alibabacloud_inference_id} for {task_type} using {service_settings}.
        slots:
          alibabacloud_inference_id: path.alibabacloud_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{amazonbedrock_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an Amazon Bedrock inference endpoint
      effect: write
      questions:
      - How do I hook Amazon Bedrock models into Elasticsearch inference?
      - Do I have to re-enter my Amazon Bedrock access and secret keys after creating the endpoint?
      instructions:
      - text: Create an Amazon Bedrock {task_type} endpoint called {amazonbedrock_inference_id}.
        slots:
          task_type: path.task_type
          amazonbedrock_inference_id: path.amazonbedrock_inference_id
      - text: Connect Amazon Bedrock as {amazonbedrock_inference_id} for {task_type} with settings {service_settings}.
        slots:
          amazonbedrock_inference_id: path.amazonbedrock_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{amazonsagemaker_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an Amazon SageMaker inference endpoint
      effect: write
      questions:
      - Can I point an Elasticsearch inference endpoint at a model hosted on Amazon SageMaker?
      - What settings does the amazon_sagemaker inference service expect?
      instructions:
      - text: Create an Amazon SageMaker {task_type} endpoint {amazonsagemaker_inference_id}.
        slots:
          task_type: path.task_type
          amazonsagemaker_inference_id: path.amazonsagemaker_inference_id
      - text: Wire my SageMaker model in as {amazonsagemaker_inference_id} for {task_type} using {service_settings}.
        slots:
          amazonsagemaker_inference_id: path.amazonsagemaker_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{anthropic_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an Anthropic inference endpoint
      effect: write
      questions:
      - How do I use Anthropic models for completion through Elasticsearch?
      - What does an anthropic inference endpoint need in its service settings?
      instructions:
      - text: Create an Anthropic {task_type} endpoint named {anthropic_inference_id}.
        slots:
          task_type: path.task_type
          anthropic_inference_id: path.anthropic_inference_id
      - text: Register Anthropic endpoint {anthropic_inference_id} for {task_type} with {service_settings}.
        slots:
          anthropic_inference_id: path.anthropic_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{azureaistudio_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an Azure AI Studio inference endpoint
      effect: write
      questions:
      - Can I use models deployed in Azure AI Studio for embeddings or completion in Elasticsearch?
      - What's required to create an azureaistudio inference endpoint?
      instructions:
      - text: Create an Azure AI Studio {task_type} endpoint {azureaistudio_inference_id}.
        slots:
          task_type: path.task_type
          azureaistudio_inference_id: path.azureaistudio_inference_id
      - text: Connect Azure AI Studio as {azureaistudio_inference_id} for {task_type} using {service_settings}.
        slots:
          azureaistudio_inference_id: path.azureaistudio_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{azureopenai_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an Azure OpenAI inference endpoint
      effect: write
      questions:
      - How do I use my Azure OpenAI deployment for embeddings or chat completion in Elasticsearch?
      - Which Azure OpenAI chat models can an azureopenai inference endpoint point at?
      instructions:
      - text: Create an Azure OpenAI {task_type} endpoint named {azureopenai_inference_id}.
        slots:
          task_type: path.task_type
          azureopenai_inference_id: path.azureopenai_inference_id
      - text: Connect my Azure OpenAI deployment as {azureopenai_inference_id} for {task_type} with {service_settings}.
        slots:
          azureopenai_inference_id: path.azureopenai_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{cohere_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a Cohere inference endpoint
      effect: write
      questions:
      - Can I use Cohere embeddings or rerank models inside Elasticsearch?
      - What goes in service_settings for a cohere inference endpoint?
      instructions:
      - text: Create a Cohere {task_type} endpoint {cohere_inference_id}.
        slots:
          task_type: path.task_type
          cohere_inference_id: path.cohere_inference_id
      - text: Register Cohere as {cohere_inference_id} for {task_type} using {service_settings}.
        slots:
          cohere_inference_id: path.cohere_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{contextualai_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a Contextual AI inference endpoint
      effect: write
      questions:
      - How do I use Contextual AI rerank models from Elasticsearch?
      - What settings does a Contextual AI rerank endpoint need?
      instructions:
      - text: Create a Contextual AI {task_type} endpoint named {contextualai_inference_id}.
        slots:
          task_type: path.task_type
          contextualai_inference_id: path.contextualai_inference_id
      - text: Set up Contextual AI reranking as {contextualai_inference_id} for {task_type} with {service_settings}.
        slots:
          contextualai_inference_id: path.contextualai_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{custom_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a custom inference endpoint
      effect: write
      questions:
      - Can I connect Elasticsearch to an inference service that has no dedicated integration?
      - How do I define my own request and response format for an external model with the custom service?
      instructions:
      - text: Create a custom {task_type} inference endpoint {custom_inference_id} for an unsupported external service.
        slots:
          task_type: path.task_type
          custom_inference_id: path.custom_inference_id
      - text: Define custom endpoint {custom_inference_id} for {task_type} with request and response settings {service_settings}.
        slots:
          custom_inference_id: path.custom_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{deepseek_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a DeepSeek inference endpoint
      effect: write
      questions:
      - Can I use DeepSeek models for completion through Elasticsearch inference?
      - What does a deepseek inference endpoint need to be configured?
      instructions:
      - text: Create a DeepSeek {task_type} endpoint {deepseek_inference_id}.
        slots:
          task_type: path.task_type
          deepseek_inference_id: path.deepseek_inference_id
      - text: Register DeepSeek as {deepseek_inference_id} for {task_type} with {service_settings}.
        slots:
          deepseek_inference_id: path.deepseek_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{elasticsearch_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an Elasticsearch-hosted model inference endpoint
      effect: write
      questions:
      - How do I deploy a model running inside my own cluster, like E5 or one uploaded with Eland, as an inference endpoint?
      - Do I need to create an endpoint for ELSER or E5 if the deployment already has preconfigured ones?
      instructions:
      - text: Create an elasticsearch-service {task_type} endpoint {elasticsearch_inference_id} for a model in my cluster.
        slots:
          task_type: path.task_type
          elasticsearch_inference_id: path.elasticsearch_inference_id
      - text: Deploy the in-cluster model as {elasticsearch_inference_id} for {task_type} with {service_settings}.
        slots:
          elasticsearch_inference_id: path.elasticsearch_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{elser_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an ELSER inference endpoint
      effect: write
      questions:
      - How do I set up an ELSER endpoint for sparse semantic search?
      - Is creating an ELSER endpoint through the elser service still the recommended way to deploy ELSER?
      instructions:
      - text: Create an ELSER {task_type} endpoint named {elser_inference_id}.
        slots:
          task_type: path.task_type
          elser_inference_id: path.elser_inference_id
      - text: Deploy ELSER as {elser_inference_id} for {task_type} with allocation settings {service_settings}.
        slots:
          elser_inference_id: path.elser_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{fireworksai_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a Fireworks AI inference endpoint
      effect: write
      questions:
      - Can I call Fireworks AI models from an Elasticsearch inference endpoint?
      - What settings does the fireworksai service require?
      instructions:
      - text: Create a Fireworks AI {task_type} endpoint {fireworksai_inference_id}.
        slots:
          task_type: path.task_type
          fireworksai_inference_id: path.fireworksai_inference_id
      - text: Register Fireworks AI as {fireworksai_inference_id} for {task_type} with {service_settings}.
        slots:
          fireworksai_inference_id: path.fireworksai_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{googleaistudio_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a Google AI Studio inference endpoint
      effect: write
      questions:
      - How do I use Google AI Studio models for completion or embeddings in Elasticsearch?
      - What does a googleaistudio endpoint need in service_settings?
      instructions:
      - text: Create a Google AI Studio {task_type} endpoint {googleaistudio_inference_id}.
        slots:
          task_type: path.task_type
          googleaistudio_inference_id: path.googleaistudio_inference_id
      - text: Connect Google AI Studio as {googleaistudio_inference_id} for {task_type} using {service_settings}.
        slots:
          googleaistudio_inference_id: path.googleaistudio_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{googlevertexai_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a Google Vertex AI inference endpoint
      effect: write
      questions:
      - Can I use Google Vertex AI embeddings or rerankers from Elasticsearch?
      - Which settings are required for a googlevertexai inference endpoint?
      instructions:
      - text: Create a Google Vertex AI {task_type} endpoint {googlevertexai_inference_id}.
        slots:
          task_type: path.task_type
          googlevertexai_inference_id: path.googlevertexai_inference_id
      - text: Connect Vertex AI as {googlevertexai_inference_id} for {task_type} with {service_settings}.
        slots:
          googlevertexai_inference_id: path.googlevertexai_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{groq_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a Groq inference endpoint
      effect: write
      questions:
      - How can I run Groq-hosted models through Elasticsearch inference?
      - What does the groq service need to create an endpoint?
      instructions:
      - text: Create a Groq {task_type} endpoint {groq_inference_id}.
        slots:
          task_type: path.task_type
          groq_inference_id: path.groq_inference_id
      - text: Register Groq as {groq_inference_id} for {task_type} with {service_settings}.
        slots:
          groq_inference_id: path.groq_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{huggingface_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a Hugging Face inference endpoint
      effect: write
      questions:
      - Can I use a Hugging Face Inference Endpoint for text embeddings in Elasticsearch?
      - Does the hugging_face service support chat_completion as well as text_embedding?
      instructions:
      - text: Create a Hugging Face {task_type} endpoint {huggingface_inference_id}.
        slots:
          task_type: path.task_type
          huggingface_inference_id: path.huggingface_inference_id
      - text: Connect my Hugging Face endpoint URL as {huggingface_inference_id} for {task_type} with {service_settings}.
        slots:
          huggingface_inference_id: path.huggingface_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{jinaai_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a JinaAI inference endpoint
      effect: write
      questions:
      - Can I use JinaAI rerankers or embedding models in Elasticsearch?
      - What goes in the settings for a jinaai inference endpoint?
      instructions:
      - text: Create a JinaAI {task_type} endpoint {jinaai_inference_id}.
        slots:
          task_type: path.task_type
          jinaai_inference_id: path.jinaai_inference_id
      - text: Register JinaAI as {jinaai_inference_id} for {task_type} with {service_settings}.
        slots:
          jinaai_inference_id: path.jinaai_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{llama_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a Llama inference endpoint
      effect: write
      questions:
      - How do I connect Llama models to Elasticsearch inference?
      - What service settings does a llama endpoint need?
      instructions:
      - text: Create a Llama {task_type} endpoint {llama_inference_id}.
        slots:
          task_type: path.task_type
          llama_inference_id: path.llama_inference_id
      - text: Register Llama as {llama_inference_id} for {task_type} with {service_settings}.
        slots:
          llama_inference_id: path.llama_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{mistral_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a Mistral inference endpoint
      effect: write
      questions:
      - Can I use Mistral embeddings or completion models in Elasticsearch?
      - What does the mistral service need in service_settings?
      instructions:
      - text: Create a Mistral {task_type} endpoint {mistral_inference_id}.
        slots:
          task_type: path.task_type
          mistral_inference_id: path.mistral_inference_id
      - text: Register Mistral as {mistral_inference_id} for {task_type} with {service_settings}.
        slots:
          mistral_inference_id: path.mistral_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{nvidia_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an Nvidia inference endpoint
      effect: write
      questions:
      - How do I use Nvidia-hosted models for inference in Elasticsearch?
      - What settings does an nvidia inference endpoint require?
      instructions:
      - text: Create an Nvidia {task_type} endpoint {nvidia_inference_id}.
        slots:
          task_type: path.task_type
          nvidia_inference_id: path.nvidia_inference_id
      - text: Register Nvidia as {nvidia_inference_id} for {task_type} with {service_settings}.
        slots:
          nvidia_inference_id: path.nvidia_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{openai_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an OpenAI inference endpoint
      effect: write
      questions:
      - Can I use OpenAI or an OpenAI-compatible API for embeddings and chat in Elasticsearch?
      - What goes in service_settings for an openai inference endpoint?
      instructions:
      - text: Create an OpenAI {task_type} endpoint {openai_inference_id}.
        slots:
          task_type: path.task_type
          openai_inference_id: path.openai_inference_id
      - text: Register an OpenAI-compatible API as {openai_inference_id} for {task_type} with {service_settings}.
        slots:
          openai_inference_id: path.openai_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{openshiftai_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create an OpenShift AI inference endpoint
      effect: write
      questions:
      - How do I connect models served on OpenShift AI to Elasticsearch inference?
      - What does the openshift_ai service need to be configured?
      instructions:
      - text: Create an OpenShift AI {task_type} endpoint {openshiftai_inference_id}.
        slots:
          task_type: path.task_type
          openshiftai_inference_id: path.openshiftai_inference_id
      - text: Register OpenShift AI as {openshiftai_inference_id} for {task_type} with {service_settings}.
        slots:
          openshiftai_inference_id: path.openshiftai_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{voyageai_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a VoyageAI inference endpoint
      effect: write
      questions:
      - Can I use VoyageAI embedding or rerank models in Elasticsearch?
      - Why shouldn't I create several VoyageAI endpoints for the same model?
      instructions:
      - text: Create a VoyageAI {task_type} endpoint {voyageai_inference_id}.
        slots:
          task_type: path.task_type
          voyageai_inference_id: path.voyageai_inference_id
      - text: Register VoyageAI as {voyageai_inference_id} for {task_type} with {service_settings}.
        slots:
          voyageai_inference_id: path.voyageai_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{watsonx_inference_id}'].put
  update:
    x-apievangelist-phrasing:
      intent: Create a watsonx inference endpoint
      effect: write
      questions:
      - How do I use IBM watsonx.ai models for inference in Elasticsearch?
      - Do I need an IBM Cloud Databases for Elasticsearch deployment to use the watsonxai service?
      instructions:
      - text: Create a watsonx {task_type} endpoint {watsonx_inference_id}.
        slots:
          task_type: path.task_type
          watsonx_inference_id: path.watsonx_inference_id
      - text: Register watsonx.ai as {watsonx_inference_id} for {task_type} with {service_settings}.
        slots:
          watsonx_inference_id: path.watsonx_inference_id
          task_type: path.task_type
          service_settings: requestBody.service_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/rerank/{inference_id}'].post
  update:
    x-apievangelist-phrasing:
      intent: Rerank documents against a query
      effect: read
      questions:
      - Can I rerank a list of candidate documents by relevance to a query?
      - Is there a way to only get back the top N results after reranking?
      - Does the rerank call return the document text or just the scores?
      instructions:
      - text: Rerank {input} against the query {query} with rerank endpoint {inference_id}.
        slots:
          input: requestBody.input
          query: requestBody.query
          inference_id: path.inference_id
      - text: Rerank these documents for {query} using {inference_id} and keep only the top {top_n}.
        slots:
          query: requestBody.query
          inference_id: path.inference_id
          top_n: requestBody.top_n
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/sparse_embedding/{inference_id}'].post
  update:
    x-apievangelist-phrasing:
      intent: Generate sparse embeddings for text
      effect: write
      questions:
      - How do I get sparse token-weight vectors for text, like ELSER produces?
      - Can I generate sparse embeddings for several strings in one request?
      instructions:
      - text: Generate sparse embeddings for {input} with endpoint {inference_id}.
        slots:
          input: requestBody.input
          inference_id: path.inference_id
      - text: Expand {input} into sparse token weights using {inference_id}.
        slots:
          input: requestBody.input
          inference_id: path.inference_id
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/completion/{inference_id}/_stream'].post
  update:
    x-apievangelist-phrasing:
      intent: Stream a text completion incrementally
      effect: write
      questions:
      - Can I stream a completion answer token by token instead of waiting for all of it?
      - Does streaming completion work with endpoints of the completion task type only?
      instructions:
      - text: Stream the completion for {input} from endpoint {inference_id} as it is generated.
        slots:
          input: requestBody.input
          inference_id: path.inference_id
      - text: Incrementally stream a completion of {input} using {inference_id}.
        slots:
          input: requestBody.input
          inference_id: path.inference_id
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/text_embedding/{inference_id}'].post
  update:
    x-apievangelist-phrasing:
      intent: Generate text embeddings for input
      effect: write
      questions:
      - How do I turn text into embedding vectors with a text_embedding endpoint?
      - Can I tell the text embedding endpoint whether my input is a search query or an ingested document?
      instructions:
      - text: Create text embeddings for {input} with text_embedding endpoint {inference_id}.
        slots:
          input: requestBody.input
          inference_id: path.inference_id
      - text: Vectorize {input} using {inference_id} with input type {input_type}.
        slots:
          input: requestBody.input
          inference_id: path.inference_id
          input_type: requestBody.input_type
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{inference_id}/_update'].put
  update:
    x-apievangelist-phrasing:
      intent: Update an inference endpoint's settings
      effect: write
      questions:
      - Can I rotate the API key stored in an existing inference endpoint?
      - How can I change task settings or the number of allocations on an endpoint without recreating it?
      instructions:
      - text: Update inference endpoint {inference_id} with new service settings {service_settings}.
        slots:
          inference_id: path.inference_id
          service_settings: requestBody.service_settings
      - text: Change the task settings of {inference_id} to {task_settings}.
        slots:
          inference_id: path.inference_id
          task_settings: requestBody.task_settings
      method: generated
      generated: '2026-09-26'
- target: $.paths['/_inference/{task_type}/{inference_id}/_update'].put
  update:
    x-apievangelist-phrasing:
      intent: Update a task-typed inference endpoint
      effect: write
      questions:
      - Can I update an inference endpoint while naming its task type in the path?
      - What parts of a text_embedding endpoint can I modify after creation?
      instructions:
      - text: Update the {task_type} endpoint {inference_id} with service settings {service_settings}.
        slots:
          task_type: path.task_type
          inference_id: path.inference_id
          service_settings: requestBody.service_settings
      - text: Modify task settings on {task_type} endpoint {inference_id} to {task_settings}.
        slots:
          task_type: path.task_type
          inference_id: path.inference_id
          task_settings: requestBody.task_settings
      method: generated
      generated: '2026-09-26'