How to Ingest PPTX with AutoGen

import json
import os
import time
import requests
from autogen import AssistantAgent, UserProxyAgent

# Step 1: Upload the PPTX file to the Ingest endpoint
with open("architecture-deck.pptx", "rb") as f:
    upload_response = requests.post(
        "https://api.enconvert.com/v2/ingest/files",
        headers={"X-API-Key": os.environ["ENCONVERT_API_KEY"]},
        files={"files": f},
    )

if upload_response.status_code == 402:
    raise RuntimeError("Ingest is not on your plan, or the monthly ops allowance is exhausted")
upload_response.raise_for_status()
job_id = upload_response.json()["job_id"]

# Step 2: Poll until the job reaches a terminal state
while True:
    status_response = requests.get(
        f"https://api.enconvert.com/v2/ingest/{job_id}",
        headers={"X-API-Key": os.environ["ENCONVERT_API_KEY"]},
    )
    status_response.raise_for_status()
    job = status_response.json()

    if job["status"] == "completed":
        break
    if job["status"] in {"failed", "canceled"}:
        raise RuntimeError(
            job.get("error_message") or f"Ingest job {job_id} ended with status {job['status']}"
        )
    time.sleep(5)

# Step 3: Download JSONL output from signed output_url (expires after 15 minutes)
jsonl_response = requests.get(job["output_url"])
jsonl_response.raise_for_status()
chunks = [json.loads(line) for line in jsonl_response.text.splitlines() if line.strip()]

# Each slide arrives as "## Slide N: Title"; speaker notes arrive as "### Notes"
# Image-only slides and blank slides are skipped entirely
# Step 4: Build context block from chunks, preserving slide and section metadata
context = "\n\n".join(
    f"[section: {c['metadata']['section']} | chunk: {c['metadata']['chunk_index']} | source: {c['metadata']['source_url']}]\n"
    f"{c.get('content')}"
    for c in chunks[:12]
)

# Step 5: Pass context into an AutoGen agent
assistant = AssistantAgent(
    name="deck_analyst",
    llm_config={"config_list": [{"model": "gpt-4.1", "api_key": os.environ["OPENAI_API_KEY"]}]},
    system_message=f"""Answer questions about the presentation using only the context provided.
Cite the slide number and section name for every claim.
Speaker notes appear as a ### Notes subsection under the slide they belong to.

Context:
{context}
""",
)

user = UserProxyAgent(
    name="user",
    human_input_mode="NEVER",
    code_execution_config=False,
)
user.initiate_chat(assistant, message="What are the key architecture decisions described in this deck?")