> ## Documentation Index
> Fetch the complete documentation index at: https://www.meilisearch.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Generate summarized answers
> Generate single, concise AI answers from your search results without maintaining conversation history.
One-shot summarization uses the same `/chats` API as multi-turn chat, but with a different prompt strategy: instead of building a conversation, you send a single question and receive a summarized answer based on your indexed documents. This is useful for displaying AI-generated answers alongside traditional search results.
Make sure you have completed the [setup guide](/capabilities/conversational_search/getting_started/setup) before continuing.
In code examples, replace `WORKSPACE_NAME` with the name of your workspace. On Meilisearch Cloud, the default workspace name is `cloud`.
All requests to the chat completions endpoint must include `"stream": true`. Non-streaming (`stream: false`) is not yet supported and returns a `501 Not Implemented` error.
## Configure your workspace prompt for summarization
The key difference from a chat interface is the system prompt. For summarization, instruct the model to produce concise, self-contained answers and avoid follow-up questions:
```bash cURL theme={null}
curl \
-X PATCH 'MEILISEARCH_URL/chats/WORKSPACE_NAME/settings' \
-H 'Authorization: Bearer MEILISEARCH_KEY' \
-H 'Content-Type: application/json' \
--data-binary '{
"prompts": {
"system": "You are a search assistant. When the user asks a question, provide a single concise answer based only on the search results. Keep your response to 2-3 sentences maximum. Do not ask follow-up questions. Do not use your general knowledge. If the search results do not contain enough information, say so briefly."
}
}'
```
Key differences from a multi-turn chat prompt:
* The system prompt explicitly asks for **short, self-contained answers**
* The model is told **not to ask follow-up questions**
* Responses are limited to a few sentences
Since the system prompt controls the answer style, we recommend creating a dedicated workspace for summarization rather than reusing a chat workspace. This keeps the prompts separate and avoids affecting other use cases. On Meilisearch Cloud, if you need a second workspace, contact our support team.
## Send a single question
Send a request to the chat completions endpoint. The difference from multi-turn chat is that you only send one message and do not maintain conversation history:
```bash cURL theme={null}
curl -N \
-X POST 'MEILISEARCH_URL/chats/WORKSPACE_NAME/chat/completions' \
-H 'Authorization: Bearer MEILISEARCH_KEY' \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "PROVIDER_MODEL_UID",
"stream": true,
"messages": [
{
"role": "user",
"content": "What is the return policy for electronics?"
}
],
"tools": [
{
"type": "function",
"function": {
"name": "_meiliSearchSources",
"description": "Provides sources of the search",
"parameters": {
"type": "object",
"properties": {
"call_id": { "type": "string", "description": "The call ID to track the original search" },
"documents": { "type": "array", "items": { "type": "object" }, "description": "The documents associated with the search" }
},
"required": ["call_id", "documents"],
"additionalProperties": false
},
"strict": true
}
}
]
}'
```
```javascript OpenAI SDK theme={null}
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'MEILISEARCH_URL/chats/WORKSPACE_NAME',
apiKey: 'MEILISEARCH_KEY',
});
const stream = await client.chat.completions.create({
model: 'PROVIDER_MODEL_UID',
messages: [{ role: 'user', content: 'What is the return policy for electronics?' }],
stream: true,
tools: [
{ type: 'function', function: { name: '_meiliSearchSources', description: 'Provides source documents' } },
],
});
let answer = '';
for await (const chunk of stream) {
const content = chunk.choices[0]?.delta?.content || '';
answer += content;
// Update the UI progressively as chunks arrive
updateSummaryBox(answer);
}
```
```javascript Vercel AI SDK theme={null}
import { createOpenAI } from '@ai-sdk/openai';
import { streamText, tool, jsonSchema } from 'ai';
const meilisearch = createOpenAI({
baseURL: 'MEILISEARCH_URL/chats/WORKSPACE_NAME',
apiKey: 'MEILISEARCH_KEY',
});
const { textStream } = streamText({
model: meilisearch('PROVIDER_MODEL_UID'),
messages: [{ role: 'user', content: 'What is the return policy for electronics?' }],
tools: {
_meiliSearchSources: tool({
description: 'Provides source documents',
parameters: jsonSchema({ type: 'object', properties: { call_id: { type: 'string' }, documents: { type: 'array', items: { type: 'object' } } }, required: ['call_id', 'documents'] }),
}),
},
});
let answer = '';
for await (const text of textStream) {
answer += text;
// Update the UI progressively as chunks arrive
updateSummaryBox(answer);
}
```
Including the `_meiliSearchSources` tool lets you display the source documents alongside the summarized answer, so users can verify the information. In a real application, you would run this in parallel with a standard Meilisearch search request and display both results together.
For summarization, you may want to use a lower `temperature` value (for example, `0.1` or `0.2`) to produce more deterministic, factual answers. Meilisearch [passes these parameters through](/capabilities/conversational_search/how_to/configure_chat_workspace#llm-provider-parameters-passthrough) to your LLM provider.
## Next steps
Create a multi-turn conversational interface with follow-up questions.
Show users which documents were used to generate the summary.
Restrict AI responses to topics covered by your data.
Learn techniques to improve accuracy of AI-generated answers.
Full reference for the chat completions endpoint.