final

api.py

@@ -15,6 +15,7 @@ from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from dotenv import load_dotenv
 from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
 import os
+from fastapi.middleware.cors import CORSMiddleware
 
 load_dotenv()
 
@@ -38,10 +39,18 @@ sentiment_model = AutoModelForSequenceClassification.from_pretrained(
 
 best_model_path = 'lib/tft_pred.ckpt'
 
-best_tft = TemporalFusionTransformer.load_from_checkpoint(best_model_path)
+best_tft = TemporalFusionTransformer.load_from_checkpoint(best_model_path).to('cpu')
 
 app = FastAPI()
 
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["GET", "POST", "PUT", "DELETE"],
+    allow_headers=["*"],
+)
+
 
 class TickerRequest(BaseModel):
     ticker: str
@@ -49,7 +58,6 @@ class TickerRequest(BaseModel):
     end_date: str
     interval: str = "1d"
 
-
 def fetch_and_process_ticker_data(ticker, start_date, end_date, interval="1d"):
     df = pd.DataFrame()
     try:
@@ -59,7 +67,8 @@ def fetch_and_process_ticker_data(ticker, start_date, end_date, interval="1d"):
         temp["revenue"] = temp["adjclose"] * temp["volume"]
         temp["daily_profit"] = temp["adjclose"] - temp["open"]
         df = pd.concat([df, temp], axis=0)
-        df.to_csv("api_test.csv", index=False)  # Save locally for reference
+        df.to_csv("api_test.csv", index=False)
+
     except Exception as error:
         raise HTTPException(
             status_code=500, detail=f"Error processing ticker {ticker}: {error}")
@@ -283,14 +292,14 @@ def get_tft_predictions(df):
     return predictions
 
 
-@app.post("/fetch-ticker-data/")
-async def fetch_ticker_data(request: TickerRequest):
+@app.get("/fetch-ticker-data/{ticker_name}/{start_date}/{end_date}/{interval}")
+async def fetch_ticker_data(ticker_name: str, start_date: str, end_date: str, interval: str):
     try:
         result_df = fetch_and_process_ticker_data(
-            ticker=request.ticker,
-            start_date=request.start_date,
-            end_date=request.end_date,
-            interval=request.interval
+            ticker=ticker_name,
+            start_date=start_date,
+            end_date=end_date,
+            interval=interval
         )
         return result_df.to_dict(orient="records")
     except Exception as e:
@@ -332,6 +341,8 @@ async def predict_prices(request: TickerRequest):
 
         sentiment_df['time_idx'] = range(1, len(sentiment_df) + 1)
 
+        print(sentiment_df)
+
         predicted_values = get_tft_predictions(sentiment_df)
 
         final_pred_open_price = predicted_values[0].item()