Spaces:
Sleeping
Sleeping
File size: 5,044 Bytes
1c70265 c569847 97ed0a5 1c70265 97ed0a5 1c70265 97ed0a5 121a026 a8c5260 3c11bf7 e65901c 1bdf384 e65901c 1bdf384 97ed0a5 121a026 1c70265 |
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 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
# rag.py
# https://github.com/vndee/local-rag-example/blob/main/rag.py
# ADAPTED TO USE HF LLM INSTEAD OF OLLAMA self.model = ChatOllama(model="mistral") BY J. BOURS 01-03-2024
# EVERNOTE:
# https://www.evernote.com/shard/s313/nl/41973486/282c6fc8-9ed5-a977-9895-1eb23941bb4c?title=REQUIREMENTS%20FOR%20A%20LITERATURE%20BASED%20RESEARCH%20LBR%20SYSTEM%20-%20FUNCTIONAL%20AND%20TECHNICAL%20REQUIREMENTS%20-%20ALEXANDER%20UNZICKER%20-%2026-02-2024
#
# mistralai/Mistral-7B-v0.1 · Hugging Face
# https://huggingface.co/mistralai/Mistral-7B-v0.1?library=true
#
# Load model directly
# from transformers import AutoTokenizer, AutoModelForCausalLM
#
# tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
# model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
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
from transformers import AutoTokenizer, AutoModelForCausalLM
class ChatPDF:
vector_store = None
retriever = None
chain = None
def __init__(self):
# self.model = ChatOllama(model="mistral") # ORIGINAL
# mistralai/Mistral-7B-v0.1 · Hugging Face
# https://huggingface.co/mistralai/Mistral-7B-v0.1?library=true
#
# Load model directly
# from transformers import AutoTokenizer, AutoModelForCausalLM
#
# tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
# model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
# TE GROOT VOOR DE FREE VERSION VAN HF SPACES (max 16 GB):
# tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
# self.model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
#
# https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha?library=true
# tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-alpha")
# self.model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-alpha")
#
# https://huggingface.co/microsoft/phi-2?library=true
# Intended Uses
# Given the nature of the training data, the Phi-2 model is best suited for prompts using the
# QA format, the chat format, and the code format.
# tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2", trust_remote_code=True)
# model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", trust_remote_code=True)
# https://huggingface.co/meta-llama/Llama-2-7b-chat-hf?library=true
#
# tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
# model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
#
# TEST EVEN ZONDER HET LADEN VAN EEN LLM !
# https://huggingface.co/stabilityai/stablelm-3b-4e1t?library=true
# tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-3b-4e1t")
# self.model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-3b-4e1t")
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 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 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=FastEmbedEmbeddings())
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 |