Una altra prova usando questo repository https://github.com/CallumJMac/lessons
Il folder di riferimento e' lessons/1. RAG/examples/pixegami /PDF_files_langchain/rag-tutorial-v2-main
I files Pdf vanno messi nel folder data
Poi si lancia populate_database.py. La persistenza e' data da ChromaDB
import argparse
import os
import shutil
from langchain.document_loaders.pdf import PyPDFDirectoryLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain.schema.document import Document
from get_embedding_function import get_embedding_function
from langchain.vectorstores.chroma import Chroma
CHROMA_PATH = "chroma"
DATA_PATH = "data"
def main():
# Check if the database should be cleared (using the --clear flag).
parser = argparse.ArgumentParser()
parser.add_argument("--reset", action="store_true", help="Reset the database.")
args = parser.parse_args()
if args.reset:
print("✨ Clearing Database")
clear_database()
# Create (or update) the data store.
documents = load_documents()
chunks = split_documents(documents)
add_to_chroma(chunks)
def load_documents():
document_loader = PyPDFDirectoryLoader(DATA_PATH)
return document_loader.load()
def split_documents(documents: list[Document]):
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=800,
chunk_overlap=80,
length_function=len,
is_separator_regex=False,
)
return text_splitter.split_documents(documents)
def add_to_chroma(chunks: list[Document]):
# Load the existing database.
db = Chroma(
persist_directory=CHROMA_PATH,
embedding_function=get_embedding_function()
)
# Calculate Page IDs.
chunks_with_ids = calculate_chunk_ids(chunks)
# Add or Update the documents.
existing_items = db.get(include=[]) # IDs are always included by default
existing_ids = set(existing_items["ids"])
print(f"Number of existing documents in DB: {len(existing_ids)}")
# Only add documents that don't exist in the DB.
new_chunks = []
for chunk in chunks_with_ids:
if chunk.metadata["id"] not in existing_ids:
new_chunks.append(chunk)
if len(new_chunks):
print(f"👉 Adding new documents: {len(new_chunks)}")
new_chunk_ids = [chunk.metadata["id"] for chunk in new_chunks]
db.add_documents(new_chunks, ids=new_chunk_ids)
db.persist()
else:
print("✅ No new documents to add")
def calculate_chunk_ids(chunks):
# This will create IDs like "data/monopoly.pdf:6:2"
# Page Source : Page Number : Chunk Index
last_page_id = None
current_chunk_index = 0
for chunk in chunks:
source = chunk.metadata.get("source")
page = chunk.metadata.get("page")
current_page_id = f"{source}:{page}"
# If the page ID is the same as the last one, increment the index.
if current_page_id == last_page_id:
current_chunk_index += 1
else:
current_chunk_index = 0
# Calculate the chunk ID.
chunk_id = f"{current_page_id}:{current_chunk_index}"
last_page_id = current_page_id
# Add it to the page meta-data.
chunk.metadata["id"] = chunk_id
return chunks
def clear_database():
if os.path.exists(CHROMA_PATH):
shutil.rmtree(CHROMA_PATH)
if __name__ == "__main__":
main()
In seguito si puo' effettuare la query da linea di comando come
python query_data.py "what's monopoly"
import argparse
from langchain.vectorstores.chroma import Chroma
from langchain.prompts import ChatPromptTemplate
from langchain_community.llms.ollama import Ollama
from get_embedding_function import get_embedding_function
CHROMA_PATH = "chroma"
PROMPT_TEMPLATE = """
Answer the question based only on the following context:
{context}
---
Answer the question based on the above context: {question}
"""
def main():
# Create CLI.
parser = argparse.ArgumentParser()
parser.add_argument("query_text", type=str, help="The query text.")
args = parser.parse_args()
query_text = args.query_text
query_rag(query_text)
def query_rag(query_text: str):
# Prepare the DB.
embedding_function = get_embedding_function()
db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
# Search the DB.
results = db.similarity_search_with_score(query_text, k=5)
context_text = "\n\n---\n\n".join([doc.page_content for doc, _score in results])
prompt_template = ChatPromptTemplate.from_template(PROMPT_TEMPLATE)
prompt = prompt_template.format(context=context_text, question=query_text)
# print(prompt)
model = Ollama(model="mistral")
response_text = model.invoke(prompt)
sources = [doc.metadata.get("id", None) for doc, _score in results]
formatted_response = f"Response: {response_text}\nSources: {sources}"
print(formatted_response)
return response_text
if __name__ == "__main__":
main()
giusto per dare un'idea questa e' la risposta
Response: Monopoly is a property trading game from Parker Brothers designed for ages 8 and up, suitable for 2 to 8 players. The gameboard is used along with tokens, houses, hotels, Chance and Community Chest cards, Title Deed cards, play money, and a Banker's tray. Players can choose to play by the classic rules or use the Speed Die for faster gameplay. In Monopoly, the objective is to become the wealthiest player by buying, renting, and selling properties.
Usando LLama3:7b la risposta e' stata
A simple one!
According to the context, Monopoly is a "Property Trading Game" from Parker Brothers.
