How to Ingest Product Specification Documents with Claude Code

import json
import os
import time
import requests
import anthropic

# Step 1: Upload the product specification document to the Ingest endpoint
with open("product-specification.docx", "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()]

# Tables and code blocks are kept whole even when they exceed the 512 word soft cap
# Step 4: Build context block from chunks, preserving heading path and section metadata
context = "\n\n".join(
    f"[section: {c['metadata']['section']} | headings: {' > '.join(c['metadata']['headings_path'])} | chunk: {c['metadata']['chunk_index']} | source: {c['metadata']['source_url']}]\n"
    f"{c.get('content')}"
    for c in chunks[:10]
)

# Step 5: Pass context into a Claude Code agent using the Anthropic SDK messages API
client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

message = client.messages.create(
    model="claude-sonnet-5-5",
    max_tokens=4096,
    system=(
        "Answer questions about the product specification using only the context provided. "
        "Cite the section path and chunk index for every claim. "
        "Quote tables and code blocks exactly as they appear in the context."
    ),
    messages=[
        {
            "role": "user",
            "content": f"Context:\n\n{context}\n\nWhat are the required fields for the create endpoint, and which section defines them?"
        }
    ],
)

for block in message.content:
    if block.type == "text":
        print(block.text)