* 1. Take the user's query as-is. * 2. Embed it using an embedding model. * 3. Use the query's embedding to search an embedding store (containing small segments of your documents) * for the X most ...
* using a technique known as "query compression". * Often, a query from a user is a follow-up question that refers back to earlier parts of the conversation * and lacks all the necessary details for ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results