> ## Documentation Index
> Fetch the complete documentation index at: https://docs.memobase.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Context-Aware Profile Search

While Memobase is designed to provide a comprehensive, global [context](/features/context) for each user with very low latency, there are times when you need to search for specific information within a user's profile.

Memobase provides a powerful, context-aware search method to filter out irrelevant memories and retrieve only what's needed for the current turn of the conversation.

## How Profile Search Works

Unlike simple keyword or semantic matching, Memobase's profile search uses the LLM to perform a feature-based analysis. It reasons about what aspects of a user's profile are relevant to their latest query.

For example, if a user asks, "Can you recommend a good restaurant?", Memobase doesn't just search for the term "restaurant." Instead, it identifies key features that would help answer the question, such as:

* `basic_info::location`: To determine the city for the restaurant search.
* `interests::food`: To understand the user's cuisine preferences.
* `health::allergies`: To know what ingredients to avoid.

This intelligent, feature-based approach results in a much more relevant and helpful set of memories than traditional search methods.

<CodeGroup>
  ```python Python theme={null}
  # Assume 'user' is an initialized MemoBaseUser object
  contextual_profile = user.profile(
      chats=[{"role": "user", "content": "Find some restaurants for me"}],
      need_json=True
  )

  print(contextual_profile)
  ```

  ```json Output theme={null}
  {
      "basic_info": {
          "location": "San Francisco",
          "allergies": "peanuts"
      },
      "interests": {
          "food": "User enjoys trying new ramen shops."
      }
  }
  ```
</CodeGroup>

See the [API Reference](/api-reference/profiles/profile#parameter-chats-str) for more details.

### Important Considerations

* **Latency**: Profile search is a powerful but computationally intensive operation. It can add **2-5 seconds** to your response time, depending on the size of the user's profile. Use it judiciously.
* **Cost**: Each profile search consumes Memobase tokens (roughly 100-1000 tokens per call), which will affect your usage costs.