Create app.py

app.py

@@ -0,0 +1,54 @@
+import logging
+import sys
+import gradio as gr
+import asyncio
+import nest_asyncio
+
+logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
+
+from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
+from llama_index.llms import HuggingFaceLLM
+from langchain.embeddings import HuggingFaceEmbeddings, HuggingFaceInstructEmbeddings 
+ 
+from g4f import Provider, models
+from langchain.llms.base import LLM
+from llama_index.llms import LangChainLLM
+from langchain_g4f import G4FLLM
+
+nest_asyncio.apply()
+"""
+documents = SimpleDirectoryReader('data').load_data()
+model_kwargs = {'device': 'cpu'}
+encode_kwargs = {'normalize_embeddings': True}
+embed_model = HuggingFaceInstructEmbeddings(
+    model_name="hkunlp/instructor-large", model_kwargs=model_kwargs,
+    encode_kwargs=encode_kwargs 
+) 
+"""
+llm= LLM = G4FLLM(
+        model=models.gpt_35_turbo,
+        provider=Provider.FreeGpt,
+    )
+
+llm = LangChainLLM(llm=llm)
+#embed_model=embed_model)
+
+service_context = ServiceContext.from_defaults(chunk_size=512, llm=llm)
+
+from llama_index import StorageContext, load_index_from_storage
+
+# rebuild storage context
+storage_context = StorageContext.from_defaults(persist_dir="./storage")
+# load index
+index = load_index_from_storage(storage_context, service_context =service_context) 
+ 
+async def main(query):
+
+    query_engine = index.as_query_engine()
+    response = query_engine.query(query)
+    print(response)
+    return response
+
+iface = gr.Interface(fn=main, inputs="text", outputs="text")
+iface.launch()