Image Analysis

pip install perplexityai

npm install @perplexity-ai/perplexity_ai

python image_analysis.py path/to/photo.jpg
python image_analysis.py https://example.com/photo.jpg

npx tsx image_analysis.ts path/to/photo.jpg
npx tsx image_analysis.ts https://example.com/photo.jpg

import sys
import base64
from perplexity import Perplexity

client = Perplexity()


def encode_image(image_path):
    """Read a local image and return a base64 data URI."""
    with open(image_path, "rb") as f:
        encoded = base64.b64encode(f.read()).decode("utf-8")
    ext = image_path.rsplit(".", 1)[-1].lower()
    mime = {"png": "image/png", "jpg": "image/jpeg", "jpeg": "image/jpeg",
            "webp": "image/webp", "gif": "image/gif"}.get(ext, "image/png")
    return f"data:{mime};base64,{encoded}"


def identify_image(image_source):
    """Step 1: Identify objects and subjects in an image."""
    image_url = image_source if image_source.startswith("http") else encode_image(image_source)

    response = client.responses.create(
        model="openai/gpt-5.6-terra",
        input=[{
            "role": "user",
            "content": [
                {
                    "type": "input_text",
                    "text": (
                        "Analyze this image in detail. Identify all notable objects, "
                        "people, landmarks, species, or text. For each, provide a "
                        "concise label and brief description. Format as a numbered list."
                    ),
                },
                {"type": "input_image", "image_url": image_url},
            ],
        }],
        max_output_tokens=1024,
    )
    return response.output_text


def research_subjects(identification_text):
    """Step 2: Research identified subjects with web search."""
    response = client.responses.create(
        model="openai/gpt-5.6-terra",
        input=(
            f"The following subjects were identified in an image:\n\n"
            f"{identification_text}\n\n"
            f"Research each subject. For each, provide:\n"
            f"- What it is and why it is notable\n"
            f"- Key facts or recent news\n"
            f"- Historical or cultural significance if applicable\n\n"
            f"Combine the analysis into a comprehensive report."
        ),
        tools=[{"type": "web_search"}],
        instructions="You are an image research assistant. Provide accurate, up-to-date information. Synthesize image observations with research.",
    )
    return response.output_text


def analyze(image_source):
    """Full pipeline: identify then research."""
    print(f"Analyzing: {image_source}\n")
    print("Step 1: Identifying subjects...")
    identification = identify_image(image_source)
    print(f"\n{identification}\n")
    print("Step 2: Researching subjects...")
    report = research_subjects(identification)
    print(f"\n{report}")


if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python image_analysis.py <image_path_or_url>")
        sys.exit(1)
    analyze(sys.argv[1])

import Perplexity from "@perplexity-ai/perplexity_ai";
import * as fs from "fs";
import * as path from "path";

const client = new Perplexity();

function encodeImage(imagePath: string): string {
  const encoded = fs.readFileSync(imagePath).toString("base64");
  const ext = path.extname(imagePath).slice(1).toLowerCase();
  const mime: Record<string, string> = {
    png: "image/png", jpg: "image/jpeg", jpeg: "image/jpeg",
    webp: "image/webp", gif: "image/gif",
  };
  return `data:${mime[ext] || "image/png"};base64,${encoded}`;
}

async function identifyImage(imageSource: string): Promise<string> {
  const imageUrl = imageSource.startsWith("http")
    ? imageSource
    : encodeImage(imageSource);

  const response = await client.responses.create({
    model: "openai/gpt-5.6-terra",
    input: [{
      role: "user",
      content: [
        {
          type: "input_text",
          text: "Analyze this image in detail. Identify all notable objects, "
            + "people, landmarks, species, or text. For each, provide a "
            + "concise label and brief description. Format as a numbered list.",
        },
        { type: "input_image", image_url: imageUrl },
      ],
    }],
    max_output_tokens: 1024,
  });
  return response.output_text;
}

async function researchSubjects(identificationText: string): Promise<string> {
  const response = await client.responses.create({
    model: "openai/gpt-5.6-terra",
    input:
      `The following subjects were identified in an image:\n\n`
      + `${identificationText}\n\n`
      + `Research each subject. For each, provide:\n`
      + `- What it is and why it is notable\n`
      + `- Key facts or recent news\n`
      + `- Historical or cultural significance if applicable\n\n`
      + `Combine the analysis into a comprehensive report.`,
    tools: [{ type: "web_search" }],
    instructions: "You are an image research assistant. Provide accurate, up-to-date information. Synthesize image observations with research.",
  });
  return response.output_text;
}

async function analyze(imageSource: string): Promise<void> {
  console.log(`Analyzing: ${imageSource}\n`);
  console.log("Step 1: Identifying subjects...");
  const identification = await identifyImage(imageSource);
  console.log(`\n${identification}\n`);
  console.log("Step 2: Researching subjects...");
  const report = await researchSubjects(identification);
  console.log(`\n${report}`);
}

const arg = process.argv[2];
if (!arg) { console.log("Usage: npx tsx image_analysis.ts <image_path_or_url>"); process.exit(1); }
analyze(arg);