Create app.py

app.py

@@ -0,0 +1,48 @@
+import gradio as gr
+from g4f import Provider, models
+from langchain.llms.base import LLM
+import asyncio
+import nest_asyncio
+from llama_index import ServiceContext, LLMPredictor, PromptHelper
+from llama_index.text_splitter import TokenTextSplitter
+from llama_index.node_parser import SimpleNodeParser
+from langchain.embeddings import HuggingFaceEmbeddings
+from llama_index import SimpleDirectoryReader
+from gradio import Interface
+nest_asyncio.apply()
+
+embed_model = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/all-mpnet-base-v2"
+)
+node_parser = SimpleNodeParser.from_defaults(text_splitter=TokenTextSplitter(chunk_size=1024, chunk_overlap=20))
+prompt_helper = PromptHelper(
+  context_window=4096,
+  num_output=256,
+  chunk_overlap_ratio=0.1,
+  chunk_size_limit=None
+)
+
+from langchain_g4f import G4FLLM
+
+async def main(question):
+    llm: LLM = G4FLLM(
+        model=models.gpt_35_turbo,
+        provider=Provider.DeepAi,
+    )
+    from llama_index.llms import LangChainLLM
+
+    llm = LangChainLLM(llm=llm)
+    
+    service_context = ServiceContext.from_defaults(llm=llm,
+  embed_model=embed_model,
+  node_parser=node_parser,
+  prompt_helper=prompt_helper)
+
+    documents = SimpleDirectoryReader("data/").load_data()
+    index = GPTVectorStoreIndex.from_documents(documents, service_context=service_context)
+    query_engine = index.as_query_engine(service_context=service_context)
+    response = query_engine.query(question)
+    return response
+
+iface = Interface(fn=main, inputs="text", outputs="text")
+iface.launch()