Docling/docling/utils/api_image_request.py
Gabe Goodhart c605edd8e9
feat: OllamaVlmModel for Granite Vision 3.2 (#1337)
* build: Add ollama sdk dependency

Branch: OllamaVlmModel

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Add option plumbing for OllamaVlmOptions in pipeline_options

Branch: OllamaVlmModel

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Full implementation of OllamaVlmModel

Branch: OllamaVlmModel

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Connect "granite_vision_ollama" pipeline option to CLI

Branch: OllamaVlmModel

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* Revert "build: Add ollama sdk dependency"

After consideration, we're going to use the generic OpenAI API instead
of the Ollama-specific API to avoid duplicate work.

This reverts commit bc6b366468cdd66b52540aac9c7d8b584ab48ad0.

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* refactor: Move OpenAI API call logic into utils.utils

This will allow reuse of this logic in a generic VLM model

NOTE: There is a subtle change here in the ordering of the text prompt and
the image in the call to the OpenAI API. When run against Ollama, this
ordering makes a big difference. If the prompt comes before the image, the
result is terse and not usable whereas the prompt coming after the image
works as expected and matches the non-OpenAI chat API.

Branch: OllamaVlmModel

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* refactor: Refactor from Ollama SDK to generic OpenAI API

Branch: OllamaVlmModel

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Linting, formatting, and bug fixes

The one bug fix was in the timeout arg to openai_image_request. Otherwise,
this is all style changes to get MyPy and black passing cleanly.

Branch: OllamaVlmModel

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* remove model from download enum

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* generalize input args for other API providers

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* rename and refactor

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add example

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* require flag for remote services

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* disable example from CI

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add examples to docs

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
2025-04-10 18:03:04 +02:00

62 lines
1.4 KiB
Python

import base64
import logging
from io import BytesIO
from typing import Dict, Optional
import requests
from PIL import Image
from pydantic import AnyUrl
from docling.datamodel.base_models import OpenAiApiResponse
_log = logging.getLogger(__name__)
def api_image_request(
image: Image.Image,
prompt: str,
url: AnyUrl,
timeout: float = 20,
headers: Optional[Dict[str, str]] = None,
**params,
) -> str:
img_io = BytesIO()
image.save(img_io, "PNG")
image_base64 = base64.b64encode(img_io.getvalue()).decode("utf-8")
messages = [
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {"url": f"data:image/png;base64,{image_base64}"},
},
{
"type": "text",
"text": prompt,
},
],
}
]
payload = {
"messages": messages,
**params,
}
headers = headers or {}
r = requests.post(
str(url),
headers=headers,
json=payload,
timeout=timeout,
)
if not r.ok:
_log.error(f"Error calling the API. Response was {r.text}")
r.raise_for_status()
api_resp = OpenAiApiResponse.model_validate_json(r.text)
generated_text = api_resp.choices[0].message.content.strip()
return generated_text