!pip install vlmrun

from pathlib import Path
from pydantic import BaseModel, Field
from vlmrun.client import VLMRun
from vlmrun.client.types import AgentExecutionResponse, AgentExecutionConfig
from vlmrun.types import MessageContent, FileUrl

# Define a Pydantic model for the execution inputs
class ExecutionInputs(BaseModel):
  file: MessageContent = Field(..., description="The file to extract data from")

# Define a Pydantic model for the response
class Invoice(BaseModel):
  invoice_id: str = Field(..., description="The ID of the invoice")
  total_amount: float = Field(..., description="The total amount of the invoice")

client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Upload the file to the object store
file = client.files.upload(file=Path("test.pdf"))

# Execute the agent (by name and version)
response: AgentExecutionResponse = client.agent.execute(
  name="<agent-name>:<agent-version>",
  inputs=ExecutionInputs(
    file=MessageContent(type="file_url", file_url=FileUrl(url=file.public_url))
  ),
  batch=True,
)

# Execute the agent (by inline prompt)
response: AgentExecutionResponse = client.agent.execute(
  inputs=ExecutionInputs(
    file=MessageContent(type="file_url", file_url=FileUrl(url=file.public_url))
  ),
  config=AgentExecutionConfig(
    prompt="Extract the invoice_id and total amount from the invoice.",
    response_model=Invoice,
  ),
  batch=True,
)

from pydantic import BaseModel, Field
from vlmrun.client import VLMRun
from vlmrun.client.types import AgentExecutionConfig, AgentExecutionResponse
from vlmrun.types import MessageContent, ImageUrl

class ExecutionInputs(BaseModel):
  image: MessageContent = Field(..., description="Image to analyze")
  instruction: MessageContent = Field(..., description="What to extract or do")

client = VLMRun(api_key="<VLMRUN_API_KEY>")

response: AgentExecutionResponse = client.agent.execute(
  name="<agent-name>:<agent-version>",
  inputs=ExecutionInputs(
    image=MessageContent(
      type="image_url",
      image_url=ImageUrl(url="https://example.com/photo.jpg", detail="high"),
    ),
    instruction=MessageContent(
      type="text",
      text="Describe the product in the image.",
    ),
  ),
  batch=True,
)

from pathlib import Path
from pydantic import BaseModel, Field
from vlmrun.client import VLMRun
from vlmrun.types import MessageContent

class ExecutionInputs(BaseModel):
  file: MessageContent = Field(..., description="Uploaded file")

client = VLMRun(api_key="<VLMRUN_API_KEY>")
file = client.files.upload(file=Path("invoice.pdf"))

response = client.agent.execute(
  name="<agent-name>:<agent-version>",
  inputs=ExecutionInputs(
    file=MessageContent(type="input_file", file_id=file.id),
  ),
  batch=True,
)

npm install vlmrun zod

import { VlmRun } from "vlmrun";

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

// Execute the agent with a file URL
const response = await client.agent.execute({
  name: "<agent-name>:<agent-version>",
  inputs: {
    file: {
      type: "file_url",
      file_url: { url: "https://example.com/invoice.pdf" },
    },
  },
  batch: true,
});

import { VlmRun } from "vlmrun";

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

const response = await client.agent.execute({
  name: "<agent-name>:<agent-version>",
  inputs: {
    image: {
      type: "image_url",
      image_url: { url: "https://example.com/photo.jpg", detail: "high" },
    },
    instruction: {
      type: "text",
      text: "Describe the product in the image.",
    },
  },
  batch: true,
});

curl -X POST https://api.vlm.run/v1/agent/execute \
  -H "Authorization: Bearer $VLMRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "<agent-name>:<agent-version>",
    "inputs": {
      "file": {
        "type": "file_url",
        "file_url": { "url": "https://example.com/invoice.pdf" }
      }
    },
    "batch": true
  }'

curl -X POST https://api.vlm.run/v1/agent/execute \
  -H "Authorization: Bearer $VLMRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "<agent-name>:<agent-version>",
    "inputs": {
      "file": { "type": "input_file", "file_id": "file_abc123" }
    },
    "batch": true
  }'

curl -X POST https://api.vlm.run/v1/agent/execute \
  -H "Authorization: Bearer $VLMRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "<agent-name>:<agent-version>",
    "inputs": {
      "image": {
        "type": "image_url",
        "image_url": { "url": "https://example.com/photo.jpg", "detail": "high" }
      },
      "instruction": {
        "type": "text",
        "text": "Describe the product in the image."
      }
    },
    "batch": true
  }'