Image to Text Agent

pip install praisonaiagents praisonai
export OPENAI_API_KEY="your-key"

from praisonaiagents import Agent, Task, PraisonAIAgents

agent = Agent(
    name="OCRAgent",
    instructions="Extract all text from images preserving layout.",
    llm="gpt-4o-mini"
)

task = Task(
    description="Extract all text from this document",
    expected_output="Extracted text",
    agent=agent,
    images=["document.jpg"]
)

agents = PraisonAIAgents(agents=[agent], tasks=[task])
result = agents.start()
print(result)

praisonai "Extract text from this document" --image document.jpg

framework: praisonai
topic: Text Extraction
roles:
  ocr_agent:
    role: OCR Specialist
    goal: Extract text from images
    backstory: You are an expert in text extraction
    llm: gpt-4o-mini
    tasks:
      extract:
        description: Extract all text from this document
        expected_output: Extracted text
        images:
          - document.jpg

praisonai agents.yaml

from praisonaiagents import Agent

agent = Agent(
    name="OCRAgent",
    instructions="You are an OCR expert.",
    llm="gpt-4o-mini"
)

agent.launch(port=8080)

curl -X POST http://localhost:8080/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Extract text from: https://example.com/doc.jpg"}'

pip install praisonaiagents praisonai pydantic
export OPENAI_API_KEY="your-key"

from praisonaiagents import Agent, Task, PraisonAIAgents, Session
from pydantic import BaseModel

class ExtractedDocument(BaseModel):
    filename: str
    text: str
    sections: list[str]
    word_count: int

session = Session(session_id="ocr-001", user_id="user-1")

agent = Agent(
    name="OCRAgent",
    instructions="Extract text and return structured results.",
    llm="gpt-4o-mini",
    memory=True
)

task = Task(
    description="Extract all text from this document",
    expected_output="Structured extraction",
    agent=agent,
    images=["document.jpg"],
    output_pydantic=ExtractedDocument
)

agents = PraisonAIAgents(
    agents=[agent],
    tasks=[task],
    memory=True,
    memory_config={"provider": "sqlite", "db_path": "ocr.db"},
    verbose=1
)

result = agents.start()
print(result)

praisonai "Extract text" --image document.jpg --memory --verbose

framework: praisonai
topic: Text Extraction
memory: true
memory_config:
  provider: sqlite
  db_path: ocr.db
roles:
  ocr_agent:
    role: OCR Specialist
    goal: Extract text with structured output
    backstory: You are an expert in text extraction
    llm: gpt-4o-mini
    memory: true
    tasks:
      extract:
        description: Extract all text from this document
        expected_output: Structured extraction
        images:
          - document.jpg
        output_json:
          filename: string
          text: string
          sections: array
          word_count: number

praisonai agents.yaml --verbose

from praisonaiagents import Agent

agent = Agent(
    name="OCRAgent",
    instructions="Extract text and return structured results.",
    llm="gpt-4o-mini",
    memory=True
)

agent.launch(port=8080)

curl -X POST http://localhost:8080/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Extract text", "session_id": "ocr-001"}'

praisonai "test ocr" --image test.jpg --verbose

rm -f ocr.db