Seamless inventory management with AI

関数呼び出しやチャット補完など、LLM AIの機能を応用し、音声やテキストによる会話を通じて店舗の在庫を管理できるAIチャットボットの作成方法を示します。

Transcript

1. Seamless inventory management with AI LINE Company (Thailand) Jorphochaudom, Phisit (Poom)
2. Demo
3. Demo by Text
4. • Use AI to convert speech to text • Use AI to think what to call (which API to use) • Use AI to extract data from JSON • Integrate with LINE Messaging API and LINE Shopping API • LINE Shopping lets Thailand sellers create a shop on LINE Official Account • We create a Rich workflow using AI In the demo summary
5. • OpenAI API • Speech to text API • Chat completion API • Function calling • Structured data extraction • LINE API • LINE Messaging API for receiving webhook and send a reply message • LINE SHOPPING API for get product listing and update inventory How?
6. What is Function Calling? • Function calling allows us to connect model to external tools • We can enhance our AI to use external functions (that we code) OpenAI Function Calling
7. Architecture LINE Webhook server OpenAI API 1. Webhook LINE Shopping API 2. Get Content 3. Audio 4. Speech to text 7. Get function call User 8. Call API 9. Send Reply Message 5. text 6. Chat completion
8. Architecture LINE Webhook server OpenAI API 1. Webhook LINE Shopping API 2. Get Content 3. Audio 4. Speech to text 7. Get function call User 8. Call API 9. Send Reply Message 5. text 6. Chat completion
9. { "destination": "xxxxxxxxxx", "events": [ { "replyToken": "nHuyWiB7yP5Zw52FIkcQobQuGDXCTA", "type": "message", "mode": "active", "timestamp": 1462629479859, "source": { "type": "user", "userId": "U4af4980629..." }, "webhookEventId": "01FZ74A0TDDPYRVKNK77XKC3ZR", "deliveryContext": { "isRedelivery": false }, "message": { "id": "325708", "type": "audio", "duration": 60000, "contentProvider": { "type": "line" } } } ] }
10. Architecture LINE Webhook server OpenAI API 1. Webhook LINE Shopping API 2. Get Content 3. Audio 4. Speech to text 7. Get function call User 8. Call API 9. Send Reply Message 5. text 6. Chat completion
11. LINE Get Content API to Get Message Content by Message ID We will get audio file and save to our local disk first
12. Architecture LINE Webhook server OpenAI API 1. Webhook LINE Shopping API 2. Get Content 3. Audio 4. Speech to text 7. Get function call User 8. Call API 9. Send Reply Message 5. text 6. Chat completion
13. LINE Get Content API to Get Message Content by Message ID curl --request POST \ --url https://api.openai.com/v1/audio/transcriptions \ --header "Authorization: Bearer $OPENAI_API_KEY" \ --header 'Content-Type: multipart/form-data' \ --form file=@/path/to/file/speech.mp3 \ --form model=whisper-1 \ --form response_format=text response text = `Can I get a product list` And we use OpenAI speech to text API
14. Architecture LINE Webhook server OpenAI API 1. Webhook LINE Shopping API 2. Get Content 3. Audio 4. Speech to text 7. Get function call User 8. Call API 9. Send Reply Message 5. text 6. Chat completion
15. Use OpenAI function calling chat completion API curl https://api.openai.com/v1/chat/completions \ --header "Authorization: Bearer $OPENAI_API_KEY" \ --header 'Content-Type: application/json‘ \ -d '{ "model": "gpt-4o", "messages": [ { "role": "user", "content": "Can I get product list" } ], "tools": [ { "type": "function", "function": { "name": "get_products", "description": "Get products in MyShop", "parameters": { "type": "object", "properties": { "ids": { "type": "string", "description": “id of products" } }, "required": [] } } } ], "tool_choice": "auto" }'
16. Tools Definition "tools": [ { "type": "function", "function": { "name": "get_products", "description": "Get products in MyShop", "parameters": { "type": "object", "properties": { "ids": { "type": "string", "description": “id of products" } }, "required": [] } } } ], "tool_choice": "auto" }'
17. OpenAI function calling chat completion API Response { "id": "chatcmpl-abc123", "object": "chat.completion", "created": 1699896916, "model": "gpt-4o-mini", "choices": [ { "index": 0, "message": { "role": "assistant", "content": null, "tool_calls": [ { "id": "call_abc123", "type": "function", "function": { "name": “get_products", "arguments": "{\n\"ids\": \"\"\n}" } } ] }, "logprobs": null, "finish_reason": "tool_calls" } ], "usage": { "prompt_tokens": 82, "completion_tokens": 17, "total_tokens": 99, "completion_tokens_details": { "reasoning_tokens": 0 } } }
18. Choices Response "choices": [ { "index": 0, "message": { "role": "assistant", "content": null, "tool_calls": [ { "id": "call_abc123", "type": "function", "function": { "name": "get_products", "arguments": "{\n\"ids\": \"\"\n}" } } ] }, "logprobs": null, "finish_reason": "tool_calls" } ],
19. Architecture LINE Webhook server OpenAI API 1. Webhook LINE Shopping API 2. Get Content 3. Audio 4. Speech to text 7. Get function call User 8. Call API 9. Send Reply Message 5. text 6. Chat completion
20. Now we know we have to get products from LINE Shopping API curl https://developers-oaplus.line.biz/myshop/v1/products \ --header “X-API-KEY: Bearer $LINE_SHOPPING_API_KEY” \ --header ‘Content-Type: application/json‘ We then use normal LINE Messaging Reply API to reply to user
21. Architecture LINE Webhook server OpenAI API 1. Webhook LINE Shopping API 2. Get Content 3. Audio 4. Speech to text 7. Get function call User 8. Call API 9. Send Reply Message 5. text 6. Chat completion
22. Update product’s inventory is the same: LINE Get Content API to Get Message Content by Message ID to get audio Use OpenAI Speech to text to convert audio to text We get “Update inventory of LINE dev t-shirt to 20”
23. Now is function calling’s job curl https://api.openai.com/v1/chat/completions \ --header "Authorization: Bearer $OPENAI_API_KEY" \ --header 'Content-Type: application/json‘ \ -d '{ "model": "gpt-4o", "messages": [ { "role": "user", "content": "Update inventory of LINE dev t-shirt to 25" } ], "tools": [ { "type": "function", "function": { "name": "update_inventory_by_name", "description": "Update product inventory in MyShop by product name", "parameters": { "type": "object", "properties": { "name": { "type": "string", "description": “name of product" }, "amount": { "type": "integer", "description": “quantity of product" } }, "required": [] } } } ], "tool_choice": "auto" }'
24. But LINE Shopping API doesn’t have update inventory by product name How do we solve this? LINE Shopping API provides only update by `inventory id`
25. Let AI solve this! We can ask AI to get all products, and find inventory id for us. 1. Call LINE shopping get products 2. Ask AI to find inventory id by product name 3. Call LINE Shopping API update inventory by id
26. curl https://api.openai.com/v1/chat/completions \ --header "Authorization: Bearer $OPENAI_API_KEY" \ --header 'Content-Type: application/json‘ \ -d '{ "model": "gpt-4o", "messages": [ { "role": "system", "content": "You are an expert at structured data extraction. You will be given json response api and should parse inventory id" }, { "role": "system", "content": "extract inventory id for $productName with following: $json" } ], "tools": [ { "type": "function", "function": { "name": "update_inventory_by_name", "description": "Update product inventory in MyShop by product name", "parameters": { "type": "object", "properties": { "name": { "type": "string", "description": “name of product" }, "amount": { "type": "integer", "description": “quantity of product" } }, "required": [] } } } ], "tool_choice": "auto" }'
27. "messages": [ { "role": "system", "content": "You are an expert at structured data extraction. You will be given json response from api and should parse inventory id" }, { "role": "system", "content": "extract inventory id for เสื้อไลน์เดฟ with following: { … // JSON … }” } ],
28. This is a combination of different techniques - We can ask AI to parse data from JSON - Then we ask them to do function calling - We then call our function in our code
29. Architecture LINE Webhook server OpenAI API 1. Webhook LINE Shopping API 2. Get Content 3. Audio 4. Speech to text 7. Get function call User 8. Call API 9. Send Reply Message 5. text 6. Chat completion
30. Pricing At what cost?
31. Pricing At what cost? { "id": "chatcmpl-abc123", "object": "chat.completion", "created": 1699896916, "model": "gpt-4o-mini", "choices": [ { "index": 0, "message": { "role": "assistant", "content": null, "tool_calls": [ { "id": "call_abc123", "type": "function", "function": { "name": “get_products", "arguments": "{\n\"ids\": \"\"\n}" } } ] }, "logprobs": null, "finish_reason": "tool_calls" } ], "usage": { "prompt_tokens": 82, "completion_tokens": 17, "total_tokens": 99, "completion_tokens_details": { "reasoning_tokens": 0 } } } Almost Free!
32. What can be improved • What if we have hundreds of products? • Using vector embedding to do text search • Using assistant API to do `thread` conversation • OpenAI now have speech to speech real-time API • We can build MCP server for product management!
33. • Use AI to convert speech to text • Use AI to think what to call (which API to use) • Use AI to extract data from JSON • Integrate with LINE Messaging API and LINE Shopping API • We create a Rich workflow using AI Summary What have we done