final

api.py

@@ -10,24 +10,9 @@ from pytorch_forecasting import TemporalFusionTransformer
 from bs4 import BeautifulSoup
 import requests
 import torch
-from llama_index.core import StorageContext, load_index_from_storage
-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()
-
-embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
-storage_context = StorageContext.from_defaults(persist_dir="rag_index")
-index = load_index_from_storage(storage_context, embed_model=embed_model)
 
-llm = HuggingFaceInferenceAPI(
-    model_name="HuggingFaceH4/zephyr-7b-alpha", token=os.getenv('HF_API')
-)
-
-query_engine = index.as_query_engine(llm=llm)
+from fastapi.middleware.cors import CORSMiddleware
 
 MODEL_PATH = "lib/20_lstm_model.h5"
 model = tf.keras.models.load_model(MODEL_PATH)
@@ -354,9 +339,9 @@ async def predict_prices(request: TickerRequest):
         raise HTTPException(status_code=500, detail=str(e))
 
 
-@app.get("/query-rag/{user_query}")
-def query_rag(user_query: str):
+# @app.get("/query-rag/{user_query}")
+# def query_rag(user_query: str):
 
-    response = query_engine.query(user_query)
+#     response = query_engine.query(user_query)
 
-    return {'message': response}
+#     return {'message': response}

requirements.txt

@@ -4,13 +4,6 @@ fastapi==0.110.2
 huggingface-hub==0.23.5
 lightning==2.4.0
 lightning-utilities==0.11.8
-llama-hub==0.0.79.post1
-llama-index
-llama-index-core
-llama-index-embeddings-huggingface
-llama-index-legacy
-llama-index-llms-huggingface
-llama-index-llms-huggingface-api
 multidict==6.0.5
 multiprocess==0.70.16
 nest-asyncio==1.6.0