نصوص الفيديو في LangChain

# pip install langchain-core requests
import requests
from langchain_core.documents import Document
 
API = "https://www.transcriptdock.com"
H = {"Authorization": "Bearer td_live_YOUR_KEY"}
 
def load_video(url: str, mode: str = "captions_only") -> list[Document]:
    """One Document per caption segment, with the video URL and start time as metadata."""
    job = requests.post(f"{API}/v1/jobs", headers={**H, "Idempotency-Key": f"lc-{url}"[:128]},
        json={"source": {"url": url}, "mode": mode}).json()
    while job["status"] not in ("succeeded", "failed", "cancelled"):
        job = requests.get(f"{API}/v1/jobs/{job['id']}", params={"wait": 25}, headers=H).json()
    if job["status"] != "succeeded":
        raise RuntimeError(job["error"]["code"])
    t = requests.get(f"{API}/v1/transcripts/{job['result_id']}", headers=H).json()
    meta = {"source": t["source"]["canonical_url"], "title": t["source"]["title"], "language": t["language"]}
    return [Document(page_content=s["text"], metadata={**meta, "start": s["start"], "end": s["end"]})
            for s in t["segments"]]
 
docs = load_video("https://www.youtube.com/watch?v=dQw4w9WgXcQ")

# pip install langchain-mcp-adapters langgraph langchain-anthropic
import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
 
async def main():
    client = MultiServerMCPClient({
        "transcriptdock": {
            "url": "https://www.transcriptdock.com/mcp",
            "transport": "streamable_http",
            "headers": {"Authorization": "Bearer td_live_YOUR_KEY"},
        }
    })
    tools = await client.get_tools()
    agent = create_react_agent("anthropic:claude-sonnet-5-5", tools)
    out = await agent.ainvoke({"messages": "Summarize https://www.youtube.com/watch?v=dQw4w9WgXcQ"})
    print(out["messages"][-1].content)
 
asyncio.run(main())