New commits

Signed-off-by: Dipankar Das <dipankardas0115@gmail.com>

app.py

@@ -1,37 +1,36 @@
 from fastapi import FastAPI
 from fastapi.responses import RedirectResponse
-from transformers import pipeline
- 
-# Create a new FastAPI app instance
+# from transformers import pipeline
+from PIL import Image
+import requests
+from transformers import AutoProcessor, Pix2StructForConditionalGeneration
+
+processor = AutoProcessor.from_pretrained("google/pix2struct-textcaps-base")
+model = Pix2StructForConditionalGeneration.from_pretrained("google/pix2struct-textcaps-base")
+
 
 app = FastAPI()
 
 @app.get("/")
 async def docs_redirect():
     return RedirectResponse(url='/docs')
-# Initialize the text generation pipeline
-# This function will be able to generate text
-# given an input.
-pipe = pipeline("text2text-generation", 
-model="google/flan-t5-small")
- 
-# Define a function to handle the GET request at `/generate`
-# The generate() function is defined as a FastAPI route that takes a 
-# string parameter called text. The function generates text based on the # input using the pipeline() object, and returns a JSON response 
-# containing the generated text under the key "output"
-# @app.get("/")
-# async def root():
-#     return {"message": "Hello World"}
 
 @app.get("/generate")
-def generate(text: str):
-    """
-    Using the text2text-generation pipeline from `transformers`, generate text
-    from the given input text. The model used is `google/flan-t5-small`, which
-    can be found [here](<https://huggingface.co/google/flan-t5-small>).
-    """
-    # Use the pipeline to generate text from the given input text
-    output = pipe(text)
-     
-    # Return the generated text in a JSON response
-    return {"output": output[0]["generated_text"]}
+def generate():
+    url = "https://www.ilankelman.org/stopsigns/australia.jpg"
+    image = Image.open(requests.get(url, stream=True).raw)
+
+    inputs = processor(images=image, return_tensors="pt")
+
+    # autoregressive generation
+    generated_ids = model.generate(**inputs, max_new_tokens=50)
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    print(generated_text)
+
+    # conditional generation
+    text = "A picture of"
+    inputs = processor(text=text, images=image, return_tensors="pt", add_special_tokens=False)
+
+    generated_ids = model.generate(**inputs, max_new_tokens=50)
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    print(generated_text)

requirements.txt

@@ -4,3 +4,4 @@ uvicorn[standard]==0.17.*
 sentencepiece==0.1.*
 torch==1.11.*
 transformers==4.*
+Pillow