Spaces:
Running
Running
File size: 2,573 Bytes
244c875 85cdbf8 244c875 85cdbf8 244c875 |
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 |
from langchain.vectorstores import Chroma
from langchain.chat_models import ChatOllama
from langchain.embeddings import FastEmbedEmbeddings
from langchain.schema.output_parser import StrOutputParser
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.schema.runnable import RunnablePassthrough
from langchain.prompts import PromptTemplate
from langchain.vectorstores.utils import filter_complex_metadata
#add new import
from langchain_community.document_loaders.csv_loader import CSVLoader
from sentence_transformers import SentenceTransformer
from langchain_community.embeddings import HuggingFaceEmbeddings
model_name = "sentence-transformers/all-mpnet-base-v2"
embedding = HuggingFaceEmbeddings(
model_name=model_name,
)
class ChatPDF:
vector_store = None
retriever = None
chain = None
def __init__(self):
self.model = ChatOllama(model="mistral")
self.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1024, chunk_overlap=100)
self.prompt = PromptTemplate.from_template(
"""
<s> [INST] You are an assistant for question-answering tasks. Use only the following pieces of retrieved context
to build an answer for the user. If you don't know the answer, just say that you don't know. Use three sentences
maximum and keep the answer concise. [/INST] </s>
[INST] Question: {question}
Context: {context}
Answer: [/INST]
"""
)
def ingest(self, pdf_file_path: str):
docs = PyPDFLoader(file_path=pdf_file_path).load()
chunks = self.text_splitter.split_documents(docs)
chunks = filter_complex_metadata(chunks)
vector_store = Chroma.from_documents(documents=chunks, embedding=embedding)
self.retriever = vector_store.as_retriever(
search_type="similarity_score_threshold",
search_kwargs={
"k": 3,
"score_threshold": 0.5,
},
)
self.chain = ({"context": self.retriever, "question": RunnablePassthrough()}
| self.prompt
| self.model
| StrOutputParser())
def ask(self, query: str):
if not self.chain:
return "Please, add a PDF document first."
return self.chain.invoke(query)
def clear(self):
self.vector_store = None
self.retriever = None
self.chain = None |