File size: 1,536 Bytes
999e17e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
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()
|