Interact without an agent object¶

In some cases, you may want to get started with Cortex Agents by using agent:run without an agent object. For example, this may be useful when you want to quickly try out a use case. For more information about the REST API, see Run agent.

1. Specify the tools you want to use in the request.

   {
       "tools": [
           {
               "tool_spec": {
                   "name": "data_model",
                   "type": "cortex_analyst_text_to_sql"
               }
           },
           {
               "tool_spec": {
                   "name": "transcript_search",
                   "type": "cortex_search"
               }
           }
       ]
   }
   

   Copy

2. Provide static arguments (resources) to the tools that Cortex Agent can use for tool calling.

   {
       "tool_resources": {
           "data_model": {
               "semantic_model_file": "@cortex_tutorial_db.public.revenue_semantic_model.yaml"
           },
           "transcript_search": {
               "name": "cortex_tutorial_db.public.contract_terms",
               "max_results": 5,
               "title_column": "TRANSCRIPT_TITLE",
               "id_column": "TRANSCRIPT_ID",
               "filter": {"@eq": {"TRANSCRIPT_TYPE": "ENTERPRISE"} }
           }
       }
   }
   

   Copy

3. Now we will specify the model and the system prompt to generate the response

   {
       "model": "claude-3-5-sonnet",
       "messages": [
           {
               "role": "system",
               "content": {
                   "type": "text",
                   "text": "You’re a friendly assistant to answer questions."
               }
           }
       ]
   }
   

   Copy

4. Create a semantic model file that will be used by the Analyst tool to access structured data. Follow steps 1 to 3 in this guide to create a Cortex Analyst semantic model Getting Started with Cortex Agents (https://quickstarts.snowflake.com/guide/getting_started_with_cortex_agents/index.html?index=..%2F..index#1)

5. Next, we set up search service for Search tool to access unstructured data. Follow step 4 to 5 in this guide to create Cortex Search Service Getting Started with Cortex Agents (https://quickstarts.snowflake.com/guide/getting_started_with_cortex_agents/index.html?index=..%2F..index#1)

6. We are now ready to interact with the Agent. You will use the messages field to send requests and receive responses

   {
       "model": "claude-3-5-sonnet",
       "messages": [
           {
               "role": "system",
               "content": [
                   {
                       "type": "text",
                       "text": "You’re a friendly assistant to answer questions"
                   }
               ]
           },
           {
               "role": "user",
               "content": [
                   {
                       "type": "text",
                       "text": "hello"
                   }
               ]
           },
           {
               "role": "assistant",
               "content": [
                   {
                       "type": "text",
                       "text": "hi there!"
                   }
               ]
           },
           {
               "role": "user",
               "content": [
                   {
                       "type": "text",
                       "text": "..."
                   }
               ]
           }
       ]
   }
   

   Copy

7. As the interaction proceeds, Agent identifies the tools and executes (service-side) to fulfill the task. In the example below, the Agent identifies Text2SQL as the tool and executes to get the SQL query. During the interaction the Agent may request a tool use for the client application (client-side). For example, the Agent specifies the SQL query that should be executed.

   {
       "role": "assistant",
       "content": [
           {
               "type": "tool_use",
               "tool_use": {
                   "tool_use_id": "tool_001",
                   "name": "cortex_analyst_text_to_sql",
                   "input": {
                       "query": "...",
                       "semantic_model_file": "..."
                   }
               }
           },
           {
               "type": "tool_results",
               "tool_results": {
                   "status": "success",
                   "tool_use_id": "tool_001",
                   "content": [
                       {
                           "type": "json",
                           "json": {
                               "sql": "select * from table"
                           }
                       }
                   ]
               }
           }
       ]
   }
   

   Copy