> ## 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.

# What is conversational search?

> Conversational search allows people to make search queries using natural languages and receive AI-generated answers grounded in your data.

<Warning>
  **Conversational search is still in early development and conversational agents can hallucinate.** LLMs may occasionally produce inaccurate or misleading answers even when the retrieved source documents are correct. Monitor responses closely in production, follow the [hallucination reduction guide](/capabilities/conversational_search/advanced/reduce_hallucination), and configure [guardrails](/capabilities/conversational_search/how_to/configure_guardrails) to minimize this risk.
</Warning>

Conversational search is an AI-powered feature built on top of Meilisearch's search engine. It works as a built-in Retrieval Augmented Generation (RAG) system: when a user asks a question, Meilisearch retrieves relevant documents from its indexes, then uses an LLM to generate a response grounded in those results.

With proper configuration, such as [system prompt engineering](/capabilities/conversational_search/advanced/reduce_hallucination#system-prompt-engineering) and [guardrails](/capabilities/conversational_search/how_to/configure_guardrails), you can ensure that responses are based on your indexed data rather than the LLM's general knowledge.

This is similar to how [Perplexity](https://www.perplexity.ai/) works: every answer comes with source documents so users can verify the information. Meilisearch brings the same pattern to your own data.

## Use cases

Conversational search supports three main use cases, all powered by the same `/chats` API route:

### Multi-turn chat

Build a full conversational interface where users ask follow-up questions and the agent maintains context across the conversation. This is ideal for knowledge bases, customer support, and documentation search.

**Example**: A user asks "What models do you support?", then follows up with "Which one is the fastest?" without restating the context.

### One-shot answer summarization

Generate a single, concise answer to a user's question without maintaining conversation history. This is useful when you want to display a summarized answer alongside traditional search results.

**Example**: A user searches "How do I reset my password?" and gets a direct answer synthesized from your help articles, displayed above the regular search results.

### RAG pipelines

Integrate Meilisearch as the retrieval layer in a broader RAG architecture. Meilisearch handles query understanding and hybrid retrieval, while your application controls the generation step.

**Example**: A product recommendation engine that retrieves matching products via Meilisearch, then uses a custom prompt to generate personalized suggestions.

## How it works

1. **Query understanding**: Meilisearch automatically transforms the user's natural language question into optimized search parameters
2. **Hybrid retrieval**: combines keyword and semantic search for better relevancy
3. **Answer generation**: your chosen LLM generates a response using only the retrieved documents as context
4. **Source attribution**: every response can include references to the source documents used to generate the answer

## Implementation strategies

### Chat completions API (recommended)

In the majority of cases, you should use the [`/chats` route](/reference/api/chats/update-chat) to build conversational search. This API consolidates the entire RAG pipeline into a single endpoint, handling retrieval, context management, and generation.

Follow the [getting started guide](/capabilities/conversational_search/getting_started/setup) to set up conversational search, then build a [chat interface](/capabilities/conversational_search/getting_started/chat) or generate [summarized answers](/capabilities/conversational_search/getting_started/one_shot_summarization). Consult the [chat completions API reference](/reference/api/chats/request-a-chat-completion) for the full list of supported parameters.

### Model Context Protocol (MCP)

An alternative method is using a Model Context Protocol (MCP) server. MCPs are designed for broader uses that go beyond answering questions, but can be useful in contexts where having up-to-date data is more important than comprehensive answers.

Follow the [dedicated MCP guide](/getting_started/integrations/mcp) if you want to implement it in your application.