Skip to main content
The quality of conversational search responses depends on three layers of configuration: the system prompt, the document template, and the index-level chat settings. Each layer shapes what the LLM receives and how it responds. This guide covers how to tune each one for better results.

​
System prompt strategies

The system prompt (set through workspace settings) defines the LLM’s overall behavior. Beyond basic guardrails, you can shape response quality with specific instructions.

​
Be specific about the domain

Generic prompts produce generic answers. Tell the LLM exactly what it is and what data it works with: 
You are a helpful assistant.
The more context the LLM has about the domain, the better it can interpret ambiguous queries and structure relevant answers.

​
Define answer structure

Tell the LLM how to format responses. This improves consistency and readability: 
When recommending products:
1. Start with a brief answer to the user's question
2. List 2-3 recommended products with their key specs
3. Explain why each product fits the user's needs
4. Mention the price range

When comparing products:
1. Create a brief comparison of the key differences
2. Recommend which product fits best based on the user's stated needs
3. Mention any trade-offs

​
Control response length

Without guidance, LLMs tend to produce long responses. Set explicit length expectations: 
Keep responses concise. For simple factual questions, answer
in 1-2 sentences. For product recommendations, use 3-5 short
paragraphs. For comparisons, use a brief list format.
Never exceed 300 words unless the user explicitly asks for
a detailed explanation.

​
Configure index chat settings

Each index has chat-specific settings that control how documents are prepared for the LLM. Configure these through the index chat settings endpoint: 
curl \
  -X PATCH 'MEILISEARCH_URL/chats/WORKSPACE_NAME/indexes/products' \
  -H 'Authorization: Bearer MEILISEARCH_KEY' \
  -H 'Content-Type: application/json' \
  --data-binary '{
    "description": "Product catalog with hiking, camping, and climbing equipment. Each product has a name, description, price, category, brand, weight, and customer rating.",
    "searchParameters": {
      "limit": 5,
      "hybrid": {
        "semanticRatio": 0.7,
        "embedder": "my-embedder"
      },
      "attributesToRetrieve": ["name", "description", "price", "category", "rating"]
    }
  }'

​
Write a good index description

The description field tells the LLM what kind of data the index contains. The LLM uses this to decide whether to search the index and how to interpret results: 
Products index.

​
Limit retrieved attributes

By default, Meilisearch sends all document attributes to the LLM. This can include irrelevant data that confuses the model or wastes tokens. Use attributesToRetrieve to send only what matters: 
{
  "searchParameters": {
    "attributesToRetrieve": ["name", "description", "price", "rating"]
  }
}
Exclude internal IDs, timestamps, image URLs, and other fields the LLM does not need for generating answers.

​
Tune search parameters for chat

Conversational queries are often longer and more natural than keyword searches. Adjust search parameters to match:
  • Higher semanticRatio (0.6-0.8): natural language questions benefit from semantic search more than keyword matching
  • Lower limit (3-5): the LLM processes fewer, more relevant documents better than many loosely related ones
  • Broader matching strategy: use "matchingStrategy": "last" (the default) to match as many terms as possible
{
  "searchParameters": {
    "limit": 5,
    "hybrid": {
      "semanticRatio": 0.7,
      "embedder": "my-embedder"
    },
    "matchingStrategy": "last"
  }
}

​
Optimize document templates for chat

If your index uses an embedder, the documentTemplate affects both embedding quality and the text the LLM sees during conversational search. A good template for chat should be readable as natural language: 
{{doc.name}} {{doc.price}} {{doc.category}}
The LLM reads these rendered templates as context. Structured, readable text helps it generate better answers. See document template best practices for detailed guidance.

​
Test and iterate

After configuring prompts and settings, test with realistic queries to evaluate quality:
  1. Factual questions: “What is the lightest 2-person tent you carry?” (should cite specific products with weights)
  2. Comparison questions: “Should I get the TrailRunner Pro or the SpeedHike 3?” (should compare features)
  3. Vague questions: “I need something for a weekend trip” (should ask clarifying questions or give broad recommendations)
  4. Out-of-scope questions: “What is the weather forecast?” (should decline politely)
For each test, evaluate:
  • Is the answer grounded in the search results?
  • Is the response length appropriate?
  • Does the formatting match your instructions?
  • Are the recommended documents relevant to the question?
Adjust the system prompt, index description, and search parameters based on what you find.

​
Next steps

Configure guardrails

Restrict responses to indexed data and defined topics

Configure index chat settings

Full reference for index-level chat configuration

Document template best practices

Write effective templates for embedding and chat