| 1 | # SPDX-License-Identifier: Apache-2.0 |
| 2 | # SPDX-FileCopyrightText: Copyright contributors to the vLLM project |
| 3 | |
| 4 | import os |
| 5 | |
| 6 | import pybase64 as base64 |
| 7 | import requests |
| 8 | |
| 9 | # This example shows how to perform an online inference that generates |
| 10 | # multimodal data. In this specific case this example will take a geotiff |
| 11 | # image as input, process it using the multimodal data processor, and |
| 12 | # perform inference. |
| 13 | # Requirements : |
| 14 | # - install TerraTorch v1.1 (or later): |
| 15 | # pip install terratorch>=v1.1 |
| 16 | # - start vllm in serving mode with the below args |
| 17 | # --model='ibm-nasa-geospatial/Prithvi-EO-2.0-300M-TL-Sen1Floods11' |
| 18 | # --skip-tokenizer-init --enforce-eager |
| 19 | # --io-processor-plugin terratorch_segmentation |
| 20 | # --enable-mm-embeds |
| 21 | |
| 22 | |
| 23 | def main(): |
| 24 | image_url = "https://huggingface.co/christian-pinto/Prithvi-EO-2.0-300M-TL-VLLM/resolve/main/valencia_example_2024-10-26.tiff" # noqa: E501 |
| 25 | server_endpoint = "http://localhost:8000/pooling" |
| 26 | |
| 27 | request_payload_url = { |
| 28 | "data": { |
| 29 | "data": image_url, |
| 30 | "data_format": "url", |
| 31 | "image_format": "tiff", |
| 32 | "out_data_format": "b64_json", |
| 33 | }, |
| 34 | "priority": 0, |
| 35 | "model": "ibm-nasa-geospatial/Prithvi-EO-2.0-300M-TL-Sen1Floods11", |
| 36 | } |
| 37 | |
| 38 | ret = requests.post(server_endpoint, json=request_payload_url) |
| 39 | |
| 40 | print(f"response.status_code: {ret.status_code}") |
| 41 | print(f"response.reason:{ret.reason}") |
| 42 | |
| 43 | response = ret.json() |
| 44 | |
| 45 | decoded_image = base64.b64decode(response["data"]["data"]) |
| 46 | |
| 47 | out_path = os.path.join(os.getcwd(), "online_prediction.tiff") |
| 48 | |
| 49 | with open(out_path, "wb") as f: |
| 50 | f.write(decoded_image) |
| 51 | |
| 52 | |
| 53 | if __name__ == "__main__": |
| 54 | main() |