Spaces:
Running
Running
File size: 2,416 Bytes
5e8fd8b aa92e24 5e8fd8b aa92e24 0ee737b f562d60 0ee737b f562d60 5e8fd8b 6ef431c 446d023 aa92e24 5e8fd8b 6ef431c 5e8fd8b f1cf709 0ee737b 9266b9a f1cf709 5e8fd8b 446d023 5e8fd8b |
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 |
from langchain_community.vectorstores import Chroma
from langchain_community.llms import Ollama
from langchain_community.embeddings import FastEmbedEmbeddings
from langchain.schema.output_parser import StrOutputParser
from langchain_community.document_loaders import PyMuPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.schema.runnable import RunnablePassthrough
from langchain.prompts import PromptTemplate
from langchain_community.vectorstores.utils import filter_complex_metadata
class ChatPDF:
vector_store = None
retriever = None
chain = None
def __init__(self):
self.model = Ollama(
model="qwen:1.8b",
keep_alive=-1,
temperature=0,
num_predict=512,
repeat_penalty=1.3,
repeat_last_n=-1
)
self.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1024, chunk_overlap=64)
self.prompt = PromptTemplate.from_template(
"""
<|im_start|> You are an assistant for question-answering tasks. Use the following pieces of retrieved context to
answer the question. If you don't know the answer, just say that you don't know. Use 512 characters
maximum and keep the answer concise.
Question: {question}
Context: {context}
Answer: <|im_end|>
"""
)
def ingest(self, pdf_file_path: str):
docs = PyMuPDFLoader(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=FastEmbedEmbeddings())
self.retriever = vector_store.as_retriever(
search_type="similarity_score_threshold",
search_kwargs={
"k": 4,
"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 |