Haystack/backend/agents/location_agent.go
John Costa 57f1e70c98 feat(agents): improving rationality by adding tool to allow the models to think through choices.
This works pretty nicely actually. I'm starting to understand how to
demistify the system prompt and have the tools the agent needs to do a
good job.
2025-04-18 15:06:20 +01:00

199 lines
6.5 KiB
Go

package agents
import (
"context"
"encoding/json"
"fmt"
"screenmark/screenmark/.gen/haystack/haystack/model"
"screenmark/screenmark/agents/client"
"screenmark/screenmark/models"
"github.com/charmbracelet/log"
)
const locationPrompt = `
Role: Location AI Assistant
Objective: Identify locations from images/text, manage a saved list, and answer user queries about saved locations using the provided tools.
The user does not want to have duplicate entries on their saved location list. So you should only create a new location if listLocation doesnt return
what would be a duplicate.
Core Logic:
**Extract Location Details:** Attempt to extract location details (like InputName, InputAddress) from the user's input.
* If no details can be extracted, inform the user and use stopAgent.
**Check for Existing Location:** If details *were* extracted:
* Use listLocations with the extracted InputName and/or InputAddress to search for potentially matching locations already saved in the list.
* If you find an existing location, you shouldn't create a duplicate. Call stopAgent when this happens.
**Decide Action based on Search Results:**
* If no existing location looks like the location on the input. You should use doesLocationExist to think about whether or not this location is a duplicate.
* If you determine it is not a duplicate, then use createLocation to create a new location for the user.
* Else, you should call stopAgent.
* If the image does not contain any location, you should use stopAgent.
* You should repeat this loop of doesLocationExist and createLocation until you've completed all locations on the image.
**Reply to user querys**
* If the user asks you a specific question, you should use the reply tool to reply to them.
`
const replyTool = `
{
"type": "function",
"function": {
"name": "reply",
"description": "Signals intent to provide information about a specific known location in response to a user's query. Use only if the user asked a question and the location's ID was found via listLocations.",
"parameters": {
"type": "object",
"properties": {
"locationId": {
"type": "string",
"description": "The unique identifier of the saved location that the user is asking about."
}
},
"required": ["locationId"]
}
}
},`
const locationTools = `
[
{
"type": "function",
"function": {
"name": "doesLocationExist",
"description": "",
"parameters": {
"type": "object",
"properties": {
"rationale": {
"type": "string",
"description": "Your reasoning as to whether or not this image contains a location that already exists in listLocations"
}
},
"required": ["rationale"]
}
}
},
{
"type": "function",
"function": {
"name": "listLocations",
"description": "Retrieves the list of the user's currently saved locations (names, addresses, IDs). Use this first to check if a location from an image already exists, or to find the ID of a location the user is asking about.",
"parameters": {
"type": "object",
"properties": {},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "createLocation",
"description": "Creates a new location with as much information as you can extract. Be precise. You should only add the parameters you can actually see on the image.",
"parameters": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The primary name of the location"
},
"address": {
"type": "string",
"description": "The address of the location"
}
},
"required": ["name"]
}
}
},
%s
{
"type": "function",
"function": {
"name": "stopAgent",
"description": "Use this tool to signal that the contact processing for the current image is complete.",
"parameters": {
"type": "object",
"properties": {},
"required": []
}
}
}
]`
func getLocationAgentTools(allowReply bool) string {
if allowReply {
return fmt.Sprintf(locationTools, replyTool)
} else {
return fmt.Sprintf(locationTools, "")
}
}
type listLocationArguments struct{}
type createLocationArguments struct {
Name string `json:"name"`
Address *string `json:"address"`
}
func NewLocationAgentWithComm(log *log.Logger, locationModel models.LocationModel) client.AgentClient {
client := NewLocationAgent(log, locationModel)
client.Options.JsonTools = getLocationAgentTools(true)
return client
}
func NewLocationAgent(log *log.Logger, locationModel models.LocationModel) client.AgentClient {
agentClient := client.CreateAgentClient(client.CreateAgentClientOptions{
SystemPrompt: locationPrompt,
JsonTools: getLocationAgentTools(false),
Log: log,
EndToolCall: "stopAgent",
})
agentClient.ToolHandler.AddTool("listLocations", func(info client.ToolHandlerInfo, args string, call client.ToolCall) (any, error) {
return locationModel.List(context.Background(), info.UserId)
})
agentClient.ToolHandler.AddTool("createLocation", func(info client.ToolHandlerInfo, _args string, call client.ToolCall) (any, error) {
args := createLocationArguments{}
err := json.Unmarshal([]byte(_args), &args)
if err != nil {
return model.Locations{}, err
}
ctx := context.Background()
// TODO: this tool could be simplier, as the model could have a SaveToImage joined with the save.
location, err := locationModel.Save(ctx, info.UserId, model.Locations{
Name: args.Name,
Address: args.Address,
})
if err != nil {
return model.Locations{}, err
}
_, err = locationModel.SaveToImage(ctx, info.ImageId, location.ID)
if err != nil {
return model.Locations{}, err
}
return location, nil
})
agentClient.ToolHandler.AddTool("reply", func(info client.ToolHandlerInfo, args string, call client.ToolCall) (any, error) {
return "ok", nil
})
agentClient.ToolHandler.AddTool("doesLocationExist", func(info client.ToolHandlerInfo, args string, call client.ToolCall) (any, error) {
return "ok", nil
})
return agentClient
}