Using PDF Input

How to send PDF and other document types to a /chat/completions endpoint.

Works for:

Vertex AI models (Gemini + Anthropic)
Bedrock Models
Anthropic API Models
OpenAI API Models
Mistral (Only using file ID of already uploaded file, similar to OpenAI file_id input)

Quick Start

Using URL

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

# PDF URL
file_url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"

response = client.chat.completions.create(
    model="bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's this file about?"},
                {
                    "type": "file",
                    "file": {
                        "file_id": file_url
                    }
                }
            ]
        }
    ]
)

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

cURL

curl https://api.haimaker.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "What'\''s this file about?"},
          {
            "type": "file",
            "file": {
              "file_id": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
            }
          }
        ]
      }
    ]
  }'

Using Base64

import base64
import requests
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

# Download and encode the PDF
url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
response = requests.get(url)
file_data = response.content
encoded_file = base64.b64encode(file_data).decode("utf-8")
base64_url = f"data:application/pdf;base64,{encoded_file}"

response = client.chat.completions.create(
    model="bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's this file about?"},
                {
                    "type": "file",
                    "file": {
                        "file_data": base64_url
                    }
                }
            ]
        }
    ]
)

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

Specifying Format

To specify the format of the document, you can use the format parameter.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

file_url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"

response = client.chat.completions.create(
    model="bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's this file about?"},
                {
                    "type": "file",
                    "file": {
                        "file_id": file_url,
                        "format": "application/pdf"
                    }
                }
            ]
        }
    ]
)

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

Using Different Models

Anthropic Claude

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.chat.completions.create(
    model="anthropic/claude-3-5-sonnet-latest",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Summarize this document"},
                {
                    "type": "file",
                    "file": {
                        "file_id": "https://example.com/document.pdf"
                    }
                }
            ]
        }
    ]
)

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

Mistral

For Mistral, use a file ID received from the files endpoint:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

# file_id received from files endpoint
file_id = "fa778e5e-46ec-4562-8418-36623fe25a71"

response = client.chat.completions.create(
    model="mistral/mistral-large-latest",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's this file about?"},
                {
                    "type": "file",
                    "file": {
                        "file_id": file_id
                    }
                }
            ]
        }
    ]
)

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

Quick Start​

Using URL​

cURL​

Using Base64​

Specifying Format​

Using Different Models​

Anthropic Claude​

Mistral​