Use OkraPDF with Claude

Upload this 10-K and tell me the total revenue:
https://www.sec.gov/Archives/edgar/data/1045810/000104581024000316/nvda-20240128.htm

Read pages 40-45 of my NVIDIA filing

Extract revenue, net income, and EPS from this 10-K as a table I can paste into Excel

Compare NVIDIA's revenue across my last 4 uploaded 10-Ks

> What was the operating margin for PepsiCo, Amazon, and AMD?

# 1. Connect (one-time)
claude mcp add -s user -t http okrapdf https://api.okrapdf.com/mcp

# 2. Upload a PDF
> "Upload https://arxiv.org/pdf/2401.04088"
#  → upload_document(url, wait=true)
#  → doc-25725cc7... complete, 853 nodes extracted

# 3. Ask a question
> "What is this paper about?"
#  → ask_document(doc-25725cc7, "What is this paper about?")
#  → "Mixtral 8x7B, a sparse mixture of experts model..." (p.1)

# 4. Parallel queries — the killer feature
> "Compare operating margins for PepsiCo, Amazon, and AMD"
#
#  Agent fires 3 calls at once:
#  ┌─ ask_document(PepsiCo)  ──→  13.3%  (FY2022, p.40)
#  ├─ ask_document(Amazon)   ──→   5.2%  (FY2019, p.38)
#  └─ ask_document(AMD)      ──→   5.4%  (FY2022, p.48)
#
#  Each doc is its own Durable Object — no shared bottleneck.
#  All three return at the same time.

# 5. Structured extraction
> "Extract revenue by segment as JSON"
#  → extract_data(doc, prompt, json_schema)
#  → { "segments": [{ "name": "PBNA", "revenue": 26213 }, ...] }

Extract key financial details from this 10-K: revenue, net income,
total assets, total liabilities, cash and equivalents, and EPS diluted.

{
  "type": "object",
  "properties": {
    "company": { "type": "string" },
    "fiscal_year_ended": { "type": "string" },
    "revenue": { "type": "string" },
    "net_income": { "type": "string" },
    "total_assets": { "type": "string" },
    "total_liabilities": { "type": "string" },
    "cash_and_equivalents": { "type": "string" },
    "eps_diluted": { "type": "string" }
  }
}

{
  "company": "NVIDIA Corporation",
  "fiscal_year_ended": "January 25, 2026",
  "revenue": "$215,938 million",
  "net_income": "$120,067 million",
  "total_assets": "$206,803 million",
  "total_liabilities": "$49,510 million",
  "cash_and_equivalents": "$10,605 million",
  "eps_diluted": "$4.90"
}

> Ask doc-abc123 "What was total revenue?" using anthropic/claude-haiku-4.5

{
  "document_id": "doc-abc123",
  "question": "What was total revenue?",
  "model": "anthropic/claude-haiku-4.5"
}

> Ask doc-abc123 "What was total revenue?" using anthropic:claude-haiku-4-5-20251001

> Extract revenue from doc-abc123. Note: amounts are in HKD millions
> and the fiscal year ends in March.

{
  "document_id": "doc-abc123",
  "prompt": "Extract annual revenue",
  "json_schema": { "type": "object", "properties": { "revenue": { "type": "string" } } },
  "instructions": "Amounts are in HKD millions. Fiscal year ends in March."
}

curl -X POST https://api.okrapdf.com/document/doc-abc123/chat/completions \
  -H "Authorization: Bearer okra_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [{"role": "user", "content": "What was total revenue?"}],
    "agentConfigOverride": {
      "llm": {"chat": {"provider": "openrouter", "model": "anthropic/claude-haiku-4.5"}}
    },
    "systemPromptSuffix": "Respond in one sentence with the page number."
  }'

curl -X POST https://api.okrapdf.com/document/doc-abc123/chat/completions \
  -H "Authorization: Bearer okra_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -H 'X-Vendor-Keys: {"anthropic": "sk-ant-..."}' \
  -d '{
    "messages": [{"role": "user", "content": "What was total revenue?"}],
    "agentConfigOverride": {
      "llm": {"chat": {"provider": "anthropic", "model": "claude-haiku-4-5-20251001"}}
    }
  }'

curl -X POST https://api.okrapdf.com/document/doc-abc123/chat/completions \
  -H "Authorization: Bearer okra_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -H 'X-Vendor-Keys: {"openai": "sk-..."}' \
  -d '{
    "messages": [{"role": "user", "content": "Extract key financials"}],
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "name": "extraction",
        "schema": {
          "type": "object",
          "properties": {
            "revenue": {"type": "string"},
            "net_income": {"type": "string"}
          }
        },
        "strict": true
      }
    },
    "agentConfigOverride": {
      "llm": {"chat": {"provider": "openai", "model": "gpt-4o"}}
    },
    "systemPromptSuffix": "Values should include currency symbol and unit."
  }'