Spaces:
Sleeping
Sleeping
File size: 2,576 Bytes
0619ee4 1ea2673 0619ee4 1ea2673 0619ee4 1ea2673 0619ee4 1ea2673 4c6babf 1ea2673 314cccb 5590af0 9bea9d1 5590af0 1ea2673 314cccb 1ea2673 7379471 1ea2673 244e6ad |
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 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import os
import json
from langchain_groq import ChatGroq
from langchain import PromptTemplate
from qdrant_client import QdrantClient
from langchain.chains import RetrievalQA
from langchain.vectorstores import Qdrant
from fastapi.responses import HTMLResponse
from fastapi.staticfiles import StaticFiles
from fastapi.encoders import jsonable_encoder
from fastapi.templating import Jinja2Templates
from fastapi import FastAPI, Request, Form, Response
from langchain.embeddings import SentenceTransformerEmbeddings
os.environ["TRANSFORMERS_FORCE_CPU"] = "true"
app = FastAPI()
templates = Jinja2Templates(directory="templates")
app.mount("/static", StaticFiles(directory="static"), name="static")
config = {
'max_new_tokens': 1024,
'context_length': 2048,
'repetition_penalty': 1.1,
'temperature': 0.1,
'top_k': 50,
'top_p': 0.9,
'stream': True,
'threads': int(os.cpu_count() / 2)
}
api_key = os.environ.get("GROQ_API_KEY")
llm = ChatGroq(
model="mixtral-8x7b-32768",
api_key=api_key,
)
print("LLM Initialized....")
prompt_template = """Use the following pieces of information to answer the user's question.
If you don't know the answer, just say that you don't know, don't try to make up an answer.
Context: {context}
Question: {question}
Only return the helpful answer below and nothing else.
Helpful answer:
"""
embeddings = SentenceTransformerEmbeddings(model_name="BAAI/bge-large-en")
url = "http://localhost:6333"
client = QdrantClient(
url=url, prefer_grpc=False
)
db = Qdrant(client=client, embeddings=embeddings, collection_name="patent_database")
prompt = PromptTemplate(template=prompt_template, input_variables=['context', 'question'])
retriever = db.as_retriever(search_kwargs={"k": 3})
@app.get("/", response_class=HTMLResponse)
async def read_root(request: Request):
return templates.TemplateResponse("index.html", {"request": request})
@app.post("/get_response")
async def get_response(query: str = Form(...)):
chain_type_kwargs = {"prompt": prompt}
qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True, chain_type_kwargs=chain_type_kwargs, verbose=True)
response = qa(query)
print(response)
answer = response['result']
source_document = response['source_documents'][0].page_content
doc = response['source_documents'][0].metadata['source']
response_data = jsonable_encoder(json.dumps({"answer": answer, "source_document": source_document, "doc": doc}))
res = Response(response_data)
return res |