File size: 2,925 Bytes
f618ddc |
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 82 83 84 85 86 87 88 89 90 |
from langchain import PromptTemplate
from langchain.chains import RetrievalQA
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.document_loaders import PyPDFLoader, DirectoryLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import DirectoryLoader,TextLoader
from langchain.llms import CTransformers
import sys
#**Step 1: Load the PDF File from Data Path****
# loader=DirectoryLoader('D:/Projects/Traf_LLM/data_traf/',
# glob= "LC.txt",
# loader_cls=PyPDFLoader)
pdf_file_path =r"D:\Projects\Traf_LLM\data_jsw\LC.pdf"
loader=PyPDFLoader(pdf_file_path)
documents=loader.load()
#print(documents)
#***Step 2: Split Text into Chunks***
text_splitter=RecursiveCharacterTextSplitter(
chunk_size=500,
chunk_overlap=50)
text_chunks=text_splitter.split_documents(documents)
print(len(text_chunks))
#**Step 3: Load the Embedding Model***
embeddings=HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2', model_kwargs={'device':'cpu'})
#**Step 4: Convert the Text Chunks into Embeddings and Create a FAISS Vector Store***
vector_store=FAISS.from_documents(text_chunks, embeddings)
##**Step 5: Find the Top 3 Answers for the Query***
query="Who is Drawee?"
docs = vector_store.similarity_search(query)
#print(docs)
llm=CTransformers(model="D:/Projects/Traf_LLM/models/llama-2-7b-chat.ggmlv3.q4_0.bin",
model_type="llama",
config={'max_new_tokens':128,
'temperature':0.01})
template="""Use the following pieces of information to answer the user's question.
If you dont know the answer just say you know, don't try to make up an answer.
Context:{context}
Question:{question}
Only return the helpful answer below and nothing else
Helpful answer
"""
qa_prompt=PromptTemplate(template=template, input_variables=['context', 'question'])
#start=timeit.default_timer()
chain = RetrievalQA.from_chain_type(llm=llm,
chain_type='stuff',
retriever=vector_store.as_retriever(search_kwargs={'k': 2}),
return_source_documents=True,
chain_type_kwargs={'prompt': qa_prompt})
#response=chain({'query': "YOLOv7 is trained on which dataset"})
#end=timeit.default_timer()
#print(f"Here is the complete Response: {response}")
#print(f"Here is the final answer: {response['result']}")
#print(f"Time to generate response: {end-start}")
while True:
user_input=input(f"prompt:")
if query=='exit':
print('Exiting')
sys.exit()
if query=='':
continue
result=chain({'query':user_input})
print(f"Answer:{result['result']}") |