File size: 1,615 Bytes
e961a39 b550edf e961a39 3d4c41f 0bf30f8 e961a39 c3c4b99 e961a39 3d4c41f e961a39 fb245d7 e961a39 46d9df9 e961a39 |
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 50 51 52 53 54 55 |
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-xl", model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs
)
llm= LLM = G4FLLM(
model=models.gpt_35_turbo,
provider=Provider.GeekGpt,
)
llm = LangChainLLM(llm=llm)
#embed_model=embed_model)
service_context = ServiceContext.from_defaults(chunk_size=512, llm=llm, embed_model=embed_model )
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() |