test

app.py

@@ -13,46 +13,46 @@ PERSIST_DIR = './storage'
 # Configure the settings
 DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-@spaces.GPU
-def setup():
-    Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-base-en-v1.5", device="cpu")
+# @spaces.GPU
+# def setup():
+#     Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-base-en-v1.5", device="cpu")
 
-    Settings.llm = HuggingFaceLLM(
-        model_name="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
-        tokenizer_name="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
-        context_window=2048,
-        max_new_tokens=256,
-        generate_kwargs={"temperature": 0.7, "top_k": 50, "top_p": 0.95},
-        device_map="auto",
-    )
+#     Settings.llm = HuggingFaceLLM(
+#         model_name="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+#         tokenizer_name="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+#         context_window=2048,
+#         max_new_tokens=256,
+#         generate_kwargs={"temperature": 0.7, "top_k": 50, "top_p": 0.95},
+#         device_map="auto",
+#     )
 
 
-# load the existing index
-@spaces.GPU
-def load_context():
-    storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
-    index = load_index_from_storage(storage_context)
-    query_engine = index.as_query_engine()
-    return query_engine
+# # load the existing index
+# @spaces.GPU
+# def load_context():
+#     storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
+#     index = load_index_from_storage(storage_context)
+#     query_engine = index.as_query_engine()
+#     return query_engine
 
 
 
-@spaces.GPU
-def chatbot_response(message, history):
-    response = query_engine.query(message)
-    return str(response)
+# @spaces.GPU
+# def chatbot_response(message, history):
+#     response = query_engine.query(message)
+#     return str(response)
 
-setup()
-query_engine = load_context()
+# setup()
+# query_engine = load_context()
 
 
-iface = gr.ChatInterface(
-    fn=chatbot_response,
-    title="UESP Lore Chatbot: CPU bound version of Phi-3-mini",
-    description="Low quality and extremely slow version of the ones you can find on the github page.: https://github.com/emarron/UESP-lore  I am not paying to have Llama3 on here.",
-    examples=["Who is Zaraphus?"],
-    cache_examples=True,
-)
+# iface = gr.ChatInterface(
+#     fn=chatbot_response,
+#     title="UESP Lore Chatbot: CPU bound version of Phi-3-mini",
+#     description="Low quality and extremely slow version of the ones you can find on the github page.: https://github.com/emarron/UESP-lore  I am not paying to have Llama3 on here.",
+#     examples=["Who is Zaraphus?"],
+#     cache_examples=True,
+# )
 
-if __name__ == "__main__":
-    iface.launch()
+# if __name__ == "__main__":
+#     iface.launch()