Update app.py

app.py

@@ -7,11 +7,10 @@ from langchain_community.llms import VLLM
 from gptcache import Cache
 from gptcache.manager.factory import manager_factory
 from gptcache.processor.pre import get_prompt
-from langchain_community.cache import GPTCache
+from langchain.callbacks import get_openai_callback
 from sklearn.metrics.pairwise import cosine_similarity
 from sentence_transformers import SentenceTransformer
 import torch
-from langchain.callbacks import get_openai_callback
 import langchain
 
 app = FastAPI()
@@ -24,7 +23,6 @@ def init_gptcache(cache_obj, llm):
     cache_obj.init(pre_embedding_func=get_prompt, data_manager=manager_factory(manager="map", data_dir=f"map_cache_{hashed_llm}"))
 
 cache = Cache()
-langchain.llm_cache = GPTCache(cache=cache)
 
 hf_token = os.environ.get("HF_TOKEN")
 
@@ -38,6 +36,8 @@ llm_models = {
 for llm_name, llm in llm_models.items():
     init_gptcache(cache, llm_name)
 
+langchain.llm_cache = langchain.cache.GPTCache(session=cache)
+
 try:
     sentence_model = SentenceTransformer('all-mpnet-base-v2', device='cpu')
 except Exception as e:
@@ -91,4 +91,4 @@ async def generateText(request: Request):
     return JSONResponse({"best_model": best_model, "text": best_response, "all_responses": all_responses})
 
 if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=5001)
+    uvicorn.run(app, host="0.0.0.0", port=7860)