Multi-Page Analysis

from vlmrun.client import VLMRun

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Analyze multi-page medical documents
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
          "role": "user",
          "content": [
            {"type": "text", "text": "Analyze this multi-page medical document set. Extract patient referral page, medical insurance card and identification form in 3 separate fields in JSON format."},
            {"type": "file_url", "file_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.agent/multi-document-input-example.pdf", "detail": "auto"}}
          ]
        }
    ]
)

print(response.choices[0].message.content)

from vlmrun.client import VLMRun
from pydantic import BaseModel, Field
from typing import Literal

# Define the response schema
class DocumentPage(BaseModel):
  page_id: int = Field(..., description="Page number (0-indexed)")
  document_type: Literal["referral", "insurance-card", "identification"]

class MultiPageResponse(BaseModel):
  pages: list[DocumentPage] = Field(..., description="List of document pages")

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Analyze multi-page document with structured output
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
          "role": "user",
          "content": [
            {"type": "text", "text": "Analyze this multi-page medical document set. Extract patient referral page, medical insurance card and identification form in 3 separate fields in JSON format."},
            {"type": "file_url", "file_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.agent/multi-document-input-example.pdf", "detail": "auto"}}
          ]
        }
    ],
    response_format={"type": "json_schema", "schema": MultiPageResponse.model_json_schema()},
)

# Validate the response
result = MultiPageResponse.model_validate_json(response.choices[0].message.content)
# >>> MultiPageResponse(pages=[DocumentPage(page_id=0, document_type="referral"), ...])

import { VlmRun } from "vlmrun";

const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Analyze this multi-page medical document set. Extract patient referral page, medical insurance card and identification form in 3 separate fields in JSON format." },
        { type: "file_url", file_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.agent/multi-document-input-example.pdf", detail: "auto" } }
      ]
    }
  ]
});

console.log(response.choices[0].message.content);

import { VlmRun } from "vlmrun";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";

// Define the response schema with Zod
const MultiPageResponseSchema = z.object({
  pages: z.array(z.object({
    page_id: z.number().int().describe("Page number (0-indexed)"),
    document_type: z.enum(["referral", "insurance-card", "identification"])
  })).describe("List of document pages")
});

// Initialize the VLMRun client
const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

// Analyze multi-page document with structured output
const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Analyze this multi-page medical document set. Extract patient referral page, medical insurance card and identification form in 3 separate fields in JSON format." },
        { type: "file_url", file_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.agent/multi-document-input-example.pdf", detail: "auto" } }
      ]
    }
  ],
  response_format: {
    type: "json_schema",
    schema: zodToJsonSchema(MultiPageResponseSchema)
  }
});

const result = MultiPageResponseSchema.parse(JSON.parse(response.choices[0].message.content));