v1

latestOpenAPI 3.0.3BSL2026-07-17133415718.8 KB

Chunk

RAG on Specified Chunks

This endpoint exists as an alternative to the topic+message resource pattern where our Trieve handles chat memory. With this endpoint, the user is responsible for providing the context window and the prompt and the conversation is ephemeral.

post/api/chunk/generate

Headers

TR-Datasetstring uuid required

The dataset id or tracking_id to use for the request. We assume you intend to use an id if the value is a valid uuid.

Request body

audio_inputstring nullable

Audio input to be used in the chat. This will be used to generate the audio tokens for the model. The default is None.

chunk_idsstring[] required

The ids of the chunks to be retrieved and injected into the context window for RAG.

frequency_penaltynumber float nullable

Frequency penalty is a number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. Default is 0.7.

highlight_resultsboolean nullable

Set highlight_results to false for a slight latency improvement (1-10ms). If not specified, this defaults to true. This will add <mark><b> tags to the chunk_html of the chunks to highlight matching splits.

image_urlsstring[] nullable

Image URLs to be used in the chat. These will be used to generate the image tokens for the model. The default is None.

max_tokensinteger nullable

The maximum number of tokens to generate in the chat completion. Default is None.

{"stackTrail":"components:schemas:GenerateOffChunksReqPayload:properties:metadata","oasType":"schema","type":"unknown","description":"Metadata is any metadata you want to associate w/ the event that is created from this request","nullable":true}

modelstring nullable

Model to use for the completion. If not specified, the default model configured for the dataset will be used.

presence_penaltynumber float nullable

Presence penalty is a number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. Default is 0.7.

promptstring nullable

Prompt will be used to tell the model what to generate in the next message in the chat. The default is 'Respond to the previous instruction and include the doc numbers that you used in square brackets at the end of the sentences that you used the docs for:'. You can also specify an empty string to leave the final message alone such that your user's final message can be used as the prompt. See docs.trieve.ai or contact us for more information.

stop_tokensstring[] nullable

Stop tokens are up to 4 sequences where the API will stop generating further tokens. Default is None.

stream_responseboolean nullable

Whether or not to stream the response. If this is set to true or not included, the response will be a stream. If this is set to false, the response will be a normal JSON response. Default is true.

temperaturenumber float nullable

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Default is 0.5.

user_idstring nullable

User ID is the id of the user who is making the request. This is used to track user interactions with the RAG results.

Example request

{
  "chunk_ids": [
    "d290f1ee-6c54-4b01-90e6-d701748f0851"
  ],
  "prev_messages": [
    {
      "content": "How do I setup RAG with Trieve?",
      "role": "user"
    }
  ],
  "prompt": "Respond to the instruction and include the doc numbers that you used in square brackets at the end of the sentences that you used the docs for:",
  "stream_response": true
}

Response

This will be a JSON response of a string containing the LLM's generated inference. Response if not streaming.