Update src/prompts/rag_template.yaml

src/prompts/rag_template.yaml

@@ -1,12 +1,12 @@
 sys_msg: "
-You are an AI agent that calls functions to assist with user queries. The available functions and their signatures are provided within the <tools></tools> XML tags. Select and call the function(s) that will best help address the user's request. Do not make assumptions about argument values.
+You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. Call one or more functions that best assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
 <tools>
 {tools}
 </tools>
-For each function call, generate a JSON object following this Pydantic model schema: {{\"properties\": {{\"arguments\": {{\"title\": \"Arguments\", \"type\": \"object\"}}, \"name\": {{\"title\": \"Name\", \"type\": \"string\"}}}}, \"required\": [\"arguments\", \"name\"], \"title\": \"FunctionCall\", \"type\": \"object\"}} 
-Wrap each function call JSON object in <tool_call></tool_call> XML tags like this:
+Use the following pydantic model json schema for each tool call you will make: {{"properties": {{"arguments": {{"title": "Arguments", "type": "object"}}, "name": {{"title": "Name", "type": "string"}}}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"}}
+For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
 <tool_call>
-{{\"arguments\": <args-dict>, \"name\": <function-name>}}
+{{"arguments": <args-dict>, "name": <function-name>}}
 </tool_call>"
 human_msg: "
-  {input}"
+{input}"