> ## Documentation Index > Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt > Use this file to discover all available pages before exploring further. # Prediction API export const LwTemplate = ({title = "Key questions to get you started", icon = "sparkles", cta = "Powered by Agent Studio", linkHref = "https://lucidworks.com/demo/?utm_source=docs&utm_medium=referral&utm_campaign=docs_cta_ai"}) => { const [isLoaded, setIsLoaded] = useState(false); useEffect(() => { const timer = setTimeout(() => { setIsLoaded(true); }, 500); return () => clearTimeout(timer); }, []); return
{isLoaded && ` }} />} Powered by Lucidworks Agent Studio
; }; The LWAI Prediction API is used to send synchronous API calls that run predictions from pre-trained models or custom models. The LWAI Prediction API supports models hosted by Lucidworks and specific third-party models. The [Lucidworks AI Use Case API](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-use-case-api) returns a list of all supported models. For more information about supported models, see [Generative AI models](/docs/lw-platform/lw-ai/lw-ai-generative-ai#generative-ai-models). You can enter the values returned in the Lucidworks AI Use Case API for the `USE_CASE` and `MODEL_ID` fields in the `/prediction` use case requests. The generic path for the Prediction API is [`/ai/prediction/USE_CASE/MODEL_ID`](#prediction-use-case-by-modelid). For detailed API specifications in Swagger/OpenAPI format, see [Platform APIs](/api-reference/get-predictions/model-predictions-by-use-case). ## Prerequisites To use this API, you need: * The unique `APPLICATION_ID` for your Lucidworks AI application, which is provided by Lucidworks. * A bearer token generated with a scope value of `machinelearning.predict`. For more information, see [Authentication API](/docs/lw-platform/lw-platform/authentication-api). * Other required fields specified in each individual use case. This section describes the prerequisites if your organization generates and manages the authentication and API keys. If your organization has opted to contract with Lucidworks to provide the API keys to execute generative AI (Gen-AI) models, see [Generative AI using Lucidworks-managed keys](/docs/lw-platform/lw-ai/lw-ai-generative-ai-using-lw-keys). ## Common parameters and fields Some parameters in the `/ai/prediction/USE_CASE/MODEL_ID` request are common to all of the generative AI (Gen-AI) use cases, such as the `modelConfig` parameter. Also referred to as hyperparameters, these fields set certain controls on the response. Refer to the [API spec](/api-reference/get-predictions/model-predictions-by-use-case) for more information. ## Prediction use case by modelId The `/ai/prediction/USE_CASE/MODEL_ID` request returns predictions for pre-trained or custom models in the specified use case format for the `modelId` in the request. Unique fields and values in the request are described in each [use case](#prediction-api-use-cases). ### Example request ```bash wrap expandable theme={"dark"} curl --request POST \ --url https://APPLICATION_ID.applications.lucidworks.com/ai/prediction/USE_CASE/MODEL_ID \ --header 'Accept: application/json' \ --header 'Content-Type: application/json' \ --header 'Authorization: Bearer ACCESS_TOKEN' --data '{ "batch": [ { "text": "Content for the model to analyze." } ], "modelConfig": [ { "temperature": 0.8, "topP": 1, "presencePenalty": 2, "frequencyPenalty": 1, "maxTokens": 1 } ] }' ``` The response varies based on the specific use case and the fields included in the request. ## Prediction API use cases The use cases available in the Lucidworks AI Prediction API are detailed in the following topics: * [Embedding use cases](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-prediction-api/embedding-prediction) * [Classification use case](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-prediction-api/classification-prediction) * [Part Number Detection use case](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-prediction-api/part-number-detection-use-case) * [Pass-through use case](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-prediction-api/passthrough-prediction) * [Retrieval-augmented generation (RAG) use case](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-prediction-api/rag-prediction) * [Standalone query rewriter use case](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-prediction-api/standalone-query-rewriter-prediction) * [Summarization use case](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-prediction-api/summarization-prediction) * [Keyword extraction use case](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-prediction-api/keyword-extraction-prediction) * [Named entity recognition (NER) use case](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-prediction-api/ner-prediction) ## Streaming with the LWAI Prediction API The Lucidworks AI (LWAI) Prediction API supports streaming responses. Streaming enables clients to receive model outputs incrementally as they are generated, improving responsiveness and interactivity for applications such as chat interfaces or live content generation. When using the synchronous LWAI Prediction API, you can enable streaming by including the appropriate request header. This allows the model’s output to be sent as a stream of Server-Sent Events (SSE) instead of a single, complete JSON payload. Fusion does not currently support streaming responses. When calling LWAI through Fusion services or pipelines, responses are returned only after the full prediction is generated, even if the underlying model supports streaming. Streaming is only available when you call the LWAI Prediction API directly. Some VPNs may interfere with streaming, buffering the events all internally and sending them together as a full streamed response, rather than passing on each event as it comes. ### Unsupported Use Cases The following use cases do not currently support streaming: * Embedding * Classification * Retrieval-augmented generation (RAG) ### Unsupported Models The following models do not support streaming: * `nu-zero-ner` * Azure-hosted models ### Enabling Streaming To enable streaming, include the following header in your request: `Accept: text/event-stream`. **Example Request:** ```bash wrap theme={"dark"} curl --request POST \ --url 'https://APPLICATION_ID.applications.lucidworks.com/ai/prediction/passthrough/MODEL_ID' \ --header 'Accept: text/event-stream' \ --header 'Content-Type: application/json' \ --header 'Authorization: Bearer ACCESS_TOKEN' \ --data '{ "batch": [ { "text": "Without explanation, please give me an example pangram. PANGRAM:" } ], "useCaseConfig": { "dataType": "text" }, "modelConfig": { "temperature": 0.3, "maxTokens": 50 } }' ``` **Example Streaming Response:** Each line of the response stream begins with data: followed by a JSON payload including a small snippet of generation that will include a type of text\_delta or completed. ```json wrap theme={"dark"} data:{"requestId":"...","delta":{"batch":0,"index":0,"output":"\"The"},"type":"response.text_delta"} data:{"requestId":"...","delta":{"batch":0,"index":1,"output":" quick"},"type":"response.text_delta"} data:{"requestId":"...","delta":{"batch":0,"index":2,"output":" brown"},"type":"response.text_delta"} data:{"requestId":"...","delta":{"batch":0,"index":3,"output":" fox"},"type":"response.text_delta"} ... ``` When the model completes, a final response.completed event is sent: ```json wrap theme={"dark"} data:{"requestId":"...","predictions":[{"tokensUsed":{"promptTokens":65,"completionTokens":11,"totalTokens":76},"response":"\"The quick brown fox jumps over the lazy dog.\""}],"type":"response.completed"} ``` **Full Response Stream:** ```json wrap expandable theme={"dark"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":0,"output":"\"The"},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":1,"output":" quick"},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":2,"output":" brown"},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":3,"output":" fox"},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":4,"output":" jumps"},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":5,"output":" over"},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":6,"output":" the"},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":7,"output":" lazy"},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":8,"output":" dog"},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","delta":{"batch":0,"index":9,"output":".\""},"type":"response.text_delta"} data:{"requestId":"f0a156a7-4a65-9bcb-9617-8633adf19a5a-0-099d531c-0d6b-4834-b605-d454352bcd0e","predictions":[{"tokensUsed":{"promptTokens":65,"completionTokens":11,"totalTokens":76},"response":"\"The quick brown fox jumps over the lazy dog.\""}],"type":"response.completed"} ``` ## Example POST requests for Prediction API use cases The topic for every [use case](#prediction-api-use-cases) contains detailed information about prerequisites and parameters along with example requests and responses. This section provides an overview of Prediction API requests. ### Generic use case Prediction API POST request When submitting a POST request for a generic use case, use the following format: `https://{APPLICATION_ID}.applications.lucidworks.com/ai/prediction/{USE_CASE}/{MODEL_ID}` This example uses `APPLICATION_ID` of `b7bcb5a5-4b6a-4fb5-b6bc-9f8cc6ab234e`. Replace the placeholder for `ACCESS_TOKEN` with the token generated in the [Authentication API](/docs/lw-platform/lw-platform/authentication-api) response. ```json theme={"dark"} curl --request POST \ --url https://b7bcb5a5-4b6a-4fb5-b6bc-9f8cc6ab234e.applications.lucidworks.com/ai/prediction/{USE_CASE}/{MODEL_ID} \ --header 'Accept: application/json' \ --header 'Content-Type: application/json' \ --header 'Authorization: Bearer {ACCESS_TOKEN}' \ --data '{ "batch": [ "text": "Content for the model to analyze." ] }' ``` ### Custom embedding use case Prediction API POST request When submitting a POST request for a custom embedding use case, use the following format: `https://{APPLICATION_ID}.applications.lucidworks.com/ai/prediction/embedding/{DEPLOYMENT_ID}` This use case request requires `APPLICATION_ID` and `DEPLOYMENT_ID`. The `DEPLOYMENT_ID` is generated when the custom embedding model is deployed. For information, see [Deployment details](/docs/lw-platform/lw-ai/lw-ai-custom-embedding-model-training/custom-model-training-user-interface#deployment-details). The custom `MODEL_ID` can also be obtained using the API as described in the following topics: * [Models API](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-models-api) * [Use Case API](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-use-case-api) This example uses `APPLICATION_ID` of `b7bcb5a5-4b6a-4fb5-b6bc-9f8cc6ab234e` and a `DEPLOYMENT_ID` of `4f10a8a7-52a4-440d-a015-70d00483ac5e`. Replace the placeholder for `ACCESS_TOKEN` with the token generated in the Authentication API response. ```json theme={"dark"} curl --request POST \ --url https://b7bcb5a5-4b6a-4fb5-b6bc-9f8cc6ab234e.applications.lucidworks.com/ai/prediction/embedding/4f10a8a7-52a4-440d-a015-70d00483ac5e \ --header 'Accept: application/json' \ --header 'Content-Type: application/json' \ --header 'Authorization: Bearer {ACCESS_TOKEN}' \ --data '{ "batch": [ "text": "Content for the model to vectorize." ] }' ``` ### Pre-trained embedding use case Prediction API POST request When submitting a POST request for a pre-trained embedding use case, use the following format: `https://{APPLICATION_ID}.applications.lucidworks.com/ai/prediction/embedding/{MODEL_ID}` This use case request requires `APPLICATION_ID` and `MODEL_ID`. The pre-trained `MODEL_ID` can also be obtained using the API as described in the following topics: * [Pre-trained embedding models](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models) * [Models API](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-models-api) * [Use Case API](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-use-case-api) This example uses `APPLICATION_ID` of `b7bcb5a5-4b6a-4fb5-b6bc-9f8cc6ab234e` and a `MODEL_ID` of `gte-small`. Replace the placeholder for `ACCESS_TOKEN` with the token generated in the Authentication API response. ```json theme={"dark"} curl --request POST \ --url https://b7bcb5a5-4b6a-4fb5-b6bc-9f8cc6ab234e.applications.lucidworks.com/ai/prediction/embedding/gte-small \ --header 'Accept: application/json' \ --header 'Content-Type: application/json' \ --header 'Authorization: Bearer {ACCESS_TOKEN}' \ --data '{ "batch": [ "text": "Content for the model to vectorize." ] }' ``` ### Generative AI use case Prediction API POST request When submitting a POST request for a generative AI use case, use the following format: `https://{APPLICATION_ID}.applications.lucidworks.com/ai/prediction/{USE_CASE}/{MODEL_ID}` This use case request requires `APPLICATION_ID` and `MODEL_ID`. For information about Gen-AI use cases and models, see: * [Generative AI](/docs/lw-platform/lw-ai/lw-ai-generative-ai) * [Use Case API](/docs/lw-platform/lw-ai/lw-ai-apis/lw-ai-use-case-api) This example uses `APPLICATION_ID` of `b7bcb5a5-4b6a-4fb5-b6bc-9f8cc6ab234e`, a `USE_CASE` of `passthrough` and a `MODEL_ID` of `llama-3-8b-instruct`. Replace the placeholder for `ACCESS_TOKEN` with the token generated in the Authentication API response. ```json theme={"dark"} curl --request POST \ --url https://b7bcb5a5-4b6a-4fb5-b6bc-9f8cc6ab234e.applications.lucidworks.com/ai/prediction/passthrough/llama-3-8b-instruct \ --header 'Accept: application/json' \ --header 'Content-Type: application/json' \ --header 'Authorization: Bearer {ACCESS_TOKEN}' \ --data '{ "batch": [ { "text": "You are a helpful utility program instructed to accomplish a word correction task. Provide the most likely suggestion to the user without a preamble or elaboration.\nPOSSIBLE_MISSPELLING: swerdfish" } ], }' ```