backend model server to serve predictions

app.py

@@ -0,0 +1,29 @@
+from fastapi import FastAPI
+from transformers import pipeline
+ 
+# Create a new FastAPI app instance
+app = FastAPI()
+ 
+# Initialize text generation pipeline - to generate text given an input.
+pipe  = pipeline(
+    "text2text-generation", 
+    model = "google/flan-t5-small"
+)
+
+
+# Endpoint route: GET request at `/generate`
+@app.get("/generate")
+def generate(text: str) -> dict:    
+    """
+    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>).
+
+    generates text based on the # input using the pipeline() object
+    returns a JSON response containing the gneerated text under the key 'output'
+    """
+    # 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"]}