Api exposed

app.py

@@ -1,24 +1,21 @@
+from fastapi import FastAPI, Request
+from pydantic import BaseModel
 from transformers import pipeline
-import gradio as gr
+import uvicorn
 
-# Load the model pipeline
+# Load model and resume
 qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-small")
-
-# Load your resume content
 with open("resume.txt", "r", encoding="utf-8") as f:
     resume_text = f.read()
 
-# Function to generate answers
-def answer_question(user_question):
-    prompt = f"Resume:\n{resume_text}\n\nQuestion: {user_question}\nAnswer:"
-    response = qa_pipeline(prompt, max_length=100)[0]["generated_text"]
-    return response.strip()
+# FastAPI setup
+app = FastAPI()
+
+class Question(BaseModel):
+    query: str
 
-# Gradio interface
-gr.Interface(
-    fn=answer_question,
-    inputs=gr.Textbox(lines=2, placeholder="Ask a question about Rence's resume..."),
-    outputs="text",
-    title="Rence's Resume Q&A Bot",
-    description="Ask questions based on Rence Abishek's resume. The bot will answer using the resume content."
-    ).launch(share=True)
+@app.post("/predict")
+async def predict(question: Question):
+    prompt = f"Resume:\n{resume_text}\n\nQuestion: {question.query}\nAnswer:"
+    result = qa_pipeline(prompt, max_length=100)[0]["generated_text"]
+    return {"answer": result.strip()}