สร้างแอป AI ด้วย OGX: Agentic API Server แบบ Open-Source

# ติดตั้ง Ollama จากนั้นดึงโมเดล
ollama pull llama3.2:3b
 
# ตั้งค่าโครงการจริง (ไม่ใช่คำสั่ง uvx ชั่วคราวจากการทดลองด่วน)
uv init docbrain && cd docbrain
uv add ogx openai

uv run ogx go

curl -k -s https://localhost:8321/v1/models | python -m json.tool
``` เนื่องจาก [OGX จะรอรับการเชื่อมต่อผ่าน HTTPS โดยเริ่มแรกและมีความปลอดภัยมาให้ในตัว](https://ogx-ai.github.io/docs/getting_started/quickstart) การทดสอบในเครื่องจึงต้องใช้แฟล็ก `-k` เพื่อข้ามการตรวจสอบใบรับรอง โดยการตอบกลับจะแสดงรายชื่อโมเดลที่เชื่อมต่อกับ Ollama อยู่
 
## การแชทพื้นฐานผ่าน Responses API
 
ตัวอย่างโค้ดพื้นฐานสำหรับการเชื่อมต่อกับเซิร์ฟเวอร์:
 
```python
import httpx
from openai import OpenAI
 
client = OpenAI(
    base_url="https://localhost:8321/v1",
    api_key="fake",
    http_client=httpx.Client(verify=False),
)
 
response = client.responses.create(
    model="ollama/llama3.2:3b",
    input="What is OGX?",
)
print(response.output_text)

# อัปโหลดเอกสาร
file = client.files.create(
    file=open("lease_agreement.pdf", "rb"),
    purpose="assistants",
)
 
# สร้าง vector store และทำดัชนีไฟล์
vector_store = client.vector_stores.create(
    name="docbrain-kb",
    file_ids=[file.id],
)
 
# ถามคำถามด้วย file search
response = client.responses.create(
    model="ollama/llama3.2:3b",
    input="Summarize the key points",
    tools=[{
        "type": "file_search",
        "vector_store_ids": [vector_store.id],
    }],
)
print(response.output_text)

# tools/action_items.py
import json
import os
from datetime import datetime, timezone
 
ACTION_ITEMS_FILE = "action_items.jsonl"
 
def save_action_item(description: str, source_document: str, priority: str = "medium") -> dict:
    """Appends one action item as a JSON line to a local file."""
    if not description.strip():
        raise ValueError("description cannot be empty")
    if priority not in ("low", "medium", "high"):
        raise ValueError(f"priority must be low, medium, or high, got '{priority}'")
 
entry = {
        "description": description.strip(),
        "source_document": source_document.strip(),
        "priority": priority,
        "flagged_at": datetime.now(timezone.utc).isoformat(),
    }
    with open(ACTION_ITEMS_FILE, "a") as f:
        f.write(json.dumps(entry) + "\n")
    return {"status": "saved", "entry": entry}
 
def list_action_items() -> list[dict]:
    """Reads back every saved action item, an empty list if none exist yet."""
    if not os.path.exists(ACTION_ITEMS_FILE):
        return []
    with open(ACTION_ITEMS_FILE) as f:
        return [json.loads(line) for line in f if line.strip()]
 
ACTION_ITEM_TOOL_SCHEMA = {
    "type": "function",
    "name": "save_action_item",
    "description": (
        "Save a genuine, concrete action item found while reviewing a document. "
        "Only call this for real, actionable tasks, not general summary points."
    ),
    "parameters": {
        "type": "object",
        "properties": {
            "description": {"type": "string", "description": "The concrete action item, in one sentence"},
            "source_document": {"type": "string", "description": "Which uploaded document this came from"},
            "priority": {"type": "string", "enum": ["low", "medium", "high"]},
        },
        "required": ["description", "source_document"],
    },
}

# docbrain.py
import httpx
import json
from openai import OpenAI
from tools.action_items import save_action_item, ACTION_ITEM_TOOL_SCHEMA
 
client = OpenAI(
    base_url="https://localhost:8321/v1",
    api_key="fake",
    http_client=httpx.Client(verify=False),
)
MODEL = "ollama/llama3.2:3b"
 
def setup_knowledge_base(file_paths: list[str]) -> str:
    file_ids = []
    for path in file_paths:
        uploaded = client.files.create(file=open(path, "rb"), purpose="assistants")
        file_ids.append(uploaded.id)
    vector_store = client.vector_stores.create(name="docbrain-kb", file_ids=file_ids)
    return vector_store.id
 
def ask(question: str, vector_store_id: str) -> str:
    response = client.responses.create(
        model=MODEL,
        input=question,
        tools=[
            {"type": "file_search", "vector_store_ids": [vector_store_id]},
            ACTION_ITEM_TOOL_SCHEMA,
        ],
    )
    for item in response.output:
        if getattr(item, "type", None) == "function_call" and item.name == "save_action_item":
            args = json.loads(item.arguments)
            save_action_item(**args)
    return response.output_text
 
if __name__ == "__main__":
    vector_store_id = setup_knowledge_base(["lease_agreement.pdf", "vendor_contract.pdf"])
    answer = ask(
        "Summarize the key terms of these documents, and flag anything "
        "that needs action before a deadline.",
        vector_store_id,
    )
    print(answer)

uv run ogx go          # เทอร์มินัลที่ 1
uv run python docbrain.py    # เทอร์มินัลที่ 2