# Feature extraction for image with a hosted model
**URL:**
**Author:**  [@avivhu](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Favivhu)%5C
**Post date:** [April 9, 2023, 8:51pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffeature-extraction-for-image-with-a-hosted-model%2F36056%2F1 "2023-04-09T20:51:04Z")
Is there any hosted model on Hugging Face that performs image feature extraction and returns the features vector (aka image2vec, image embedding)?
I came across this one that is documented to do just that:
[florentgbelidji/blip\_image\_embeddings · Hugging Face](https://huggingface.co/florentgbelidji/blip_image_embeddings)
But when I called it I got an error:
`{'error': ['value is not a valid list: ` __root__ ` in `parameters`', 'str type expected: ` __root__ ` in `parameters`']}`
The test code:
```auto
import json
from typing import List
import requests as r
import base64
ENDPOINT_URL = "/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fflorentgbelidji%2Fblip_image_embeddings"
def predict(path_to_image: str):
with open(path_to_image, "rb") as i:
b64 = base64.b64encode(i.read())
payload = {"inputs": {"image": b64.decode("utf-8")}}
response = r.post(
ENDPOINT_URL, headers={"Authorization": f"Bearer {API_TOKEN}"}, json=payload
)
return response.json()
prediction = predict(path_to_image=img)
print(prediction)
```
---
**Author:**  [@radames](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fradames)%5C
**Post date:** [April 10, 2023, 8:46pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffeature-extraction-for-image-with-a-hosted-model%2F36056%2F2 "2023-04-10T20:46:49Z")
hi @avivhu ,
I don’t think we have a feature-extration from images on our community pipelines, i.e. using our API Inference. The model you’ve linked is an example of a custom pipeline for our [Inference Endpoints](https://huggingface.co/inference-endpoints), cc @florentgbelidji the author.
If you want it on our community API, for tests and prototypes you can open an issue here [Issues · huggingface/api-inference-community · GitHub](https://github.com/huggingface/api-inference-community/issues)
---
**Author:**  [@avivhu](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Favivhu)%5C
**Post date:** [April 11, 2023, 9:55am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffeature-extraction-for-image-with-a-hosted-model%2F36056%2F3 "2023-04-11T09:55:12Z")
Thanks @radames .
I opened a feature request here:
[Add image feature extraction to the Inference API [img2vec] · Issue #229 · huggingface/api-inference-community (github.com)](https://github.com/huggingface/api-inference-community/issues/229)
---
**Author:**  [@radames](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fradames)%5C
**Post date:** [April 11, 2023, 6:19pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffeature-extraction-for-image-with-a-hosted-model%2F36056%2F4 "2023-04-11T18:19:56Z")
hi @avivhu , sorry I was able to update the custom pipeline to make it work on our public API,
You can use from this model repo now, [radames/blip\_image\_embeddings · Hugging Face](https://huggingface.co/radames/blip_image_embeddings)
```python
import json
from typing import List
import requests as r
import base64
ENDPOINT_URL = "/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fradames%2Fblip_image_embeddings"
HF_TOKEN = ""
def predict(path_to_image: str = None):
with open(path_to_image, "rb") as i:
b64 = base64.b64encode(i.read())
payload = {"inputs": b64.decode("utf-8")}
response = r.post(
ENDPOINT_URL, headers={"X-Wait-For-Model": "true", "Authorization": f"Bearer {HF_TOKEN}"}, json=payload
)
return response.json()
prediction = predict(
path_to_image="palace.jpg"
)
```
---
**Author:**  [@avivhu](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Favivhu)%5C
**Post date:** [April 12, 2023, 3:07pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffeature-extraction-for-image-with-a-hosted-model%2F36056%2F5 "2023-04-12T15:07:24Z")
That works perfectly. Thank you @radames .
---
**Author:**  [@radames](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fradames)%5C
**Post date:** [December 20, 2023, 7:18pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffeature-extraction-for-image-with-a-hosted-model%2F36056%2F6 "2023-12-20T19:18:12Z")
Split this topic on December 20, 2023, 7:18pm UTC
A post was split to a new topic: [Deploying CLIP-Vit as an inference endpoint](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdeploying-clip-vit-as-an-inference-endpoint%2F66511)
---
**Author:**  [@timschott](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftimschott)%5C
**Post date:** [September 20, 2024, 7:47pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffeature-extraction-for-image-with-a-hosted-model%2F36056%2F7 "2024-09-20T19:47:34Z")
Hello! Trying this out and currently seeing
```auto
radames/blip_image_embeddings does not appear to have a file named config.json. Checkout 'https://huggingface.co/radames/blip_image_embeddings/tree/dace0eb439798ee47c0dc90f45c790ef87514770' for available files.
```
Any ideas on a fix for this?