update

.gitignore

@@ -1 +1,2 @@
 .env
+__pycache__

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.10.12
+
+WORKDIR /app
+
+COPY . /app
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+EXPOSE 8000
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
+

main.py

@@ -0,0 +1,65 @@
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
+import torch
+from datasets import load_dataset
+import pandas as pd
+import re
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+
+
+app = FastAPI()
+
+# Load your model and tokenizer
+tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+model = GPT2LMHeadModel.from_pretrained("gpt2")
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+# Add CORS middleware to allow any origin
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Allows all origins
+    allow_credentials=True,
+    allow_methods=["*"],  # Allows all methods (GET, POST, etc.)
+    allow_headers=["*"],  # Allows all headers
+)
+
+@app.get("/")
+def root():
+    return {"Hello": "World"}
+
+# Define the Pydantic model to parse JSON input
+class HistoryRequest(BaseModel):
+    user: list[str]
+    ai: list[str]
+
+@app.post("/generate")
+def generate_response(history: HistoryRequest):
+    combined_prompt = ""
+    
+    # Iterate over user and AI messages
+    for user_message, ai_message in zip(history.user, history.ai):
+        combined_prompt += f"<user> {user_message}\n<AI> {ai_message}\n"
+
+    # Include the last user message in the prompt for response generation
+    if history.user:
+        combined_prompt += f"<user> {history.user[-1]}\n<AI>"
+
+    # Tokenize and generate response
+    inputs = tokenizer.encode(combined_prompt, return_tensors="pt").to(device)
+    outputs = model.generate(
+        inputs,
+        max_length=150,  # Adjust length as needed
+        num_beams=5,
+        early_stopping=True,
+        no_repeat_ngram_size=2,
+        temperature=0.7,
+        top_k=50,
+        top_p=0.95
+    )
+
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    response = response.replace(combined_prompt, "").split(".")[0]
+    return response

requirements.txt

@@ -0,0 +1,7 @@
+requests
+transformers==4.42.4
+torch==2.3.1
+datasets==2.21.0
+pandas==2.1.4
+uvicorn[standard]
+fastapi[all]