Spaces:
Sleeping
Sleeping
first commit
Browse files- .DS_Store +0 -0
- app.py +87 -0
- ingest.py +11 -0
- rag.ipynb +1060 -0
- requirements.txt +5 -0
- vectorstore/c96ac4dc-364a-4b68-9ffb-04f2ea25be4c/data_level0.bin +3 -0
- vectorstore/c96ac4dc-364a-4b68-9ffb-04f2ea25be4c/header.bin +3 -0
- vectorstore/c96ac4dc-364a-4b68-9ffb-04f2ea25be4c/length.bin +3 -0
- vectorstore/c96ac4dc-364a-4b68-9ffb-04f2ea25be4c/link_lists.bin +0 -0
.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
app.py
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
from sentence_transformers import SentenceTransformer
|
| 3 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
|
| 4 |
+
import chromadb
|
| 5 |
+
from chromadb.config import Settings
|
| 6 |
+
import torch
|
| 7 |
+
|
| 8 |
+
st.set_page_config(page_title="RAG Chatbot", page_icon="🤖", layout="wide")
|
| 9 |
+
|
| 10 |
+
st.title("🤖 RAG Chatbot – INSIEL")
|
| 11 |
+
|
| 12 |
+
@st.cache_resource
|
| 13 |
+
def load_models():
|
| 14 |
+
# Embedding model
|
| 15 |
+
embedder = SentenceTransformer("sentence-transformers/distiluse-base-multilingual-cased-v1")
|
| 16 |
+
|
| 17 |
+
# LLM model (TinyLlama su CPU)
|
| 18 |
+
model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
|
| 19 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 20 |
+
model = AutoModelForCausalLM.from_pretrained(model_id).to(torch.device("cpu"))
|
| 21 |
+
rag_chat = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=300, device=-1)
|
| 22 |
+
|
| 23 |
+
return embedder, rag_chat
|
| 24 |
+
|
| 25 |
+
embedder, rag_chat = load_models()
|
| 26 |
+
|
| 27 |
+
# --- CHROMA DB SETUP ---
|
| 28 |
+
#client = chromadb.PersistentClient(path="./vectorstore")
|
| 29 |
+
|
| 30 |
+
#collection = client.get_or_create_collection("insiel_chunks")
|
| 31 |
+
|
| 32 |
+
client = chromadb.PersistentClient(path="./vectorstore")
|
| 33 |
+
collection = client.get_or_create_collection(name="insiel_chunks")
|
| 34 |
+
|
| 35 |
+
# --- FUNZIONE DI RISPOSTA ---
|
| 36 |
+
|
| 37 |
+
def generate_rag_response_local(query, retrieved_chunks):
|
| 38 |
+
context = "\n\n".join(retrieved_chunks)
|
| 39 |
+
context = context[:3000] # taglia se troppo lungo per evitare overflow
|
| 40 |
+
|
| 41 |
+
prompt = (
|
| 42 |
+
"Rispondi alla domanda usando solo le informazioni nel contesto. "
|
| 43 |
+
"Se la risposta non è presente, di' chiaramente che non è specificato nel documento.\n\n"
|
| 44 |
+
f"Contesto:\n{context}\n\n"
|
| 45 |
+
f"Domanda: \n{query}\n"
|
| 46 |
+
"Risposta:"
|
| 47 |
+
)
|
| 48 |
+
|
| 49 |
+
result = rag_chat(prompt)[0]["generated_text"]
|
| 50 |
+
|
| 51 |
+
return result.split("Risposta:")[-1].strip()
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
# --- INTERFACCIA ---
|
| 55 |
+
|
| 56 |
+
if "history" not in st.session_state:
|
| 57 |
+
st.session_state.history = []
|
| 58 |
+
|
| 59 |
+
query = st.text_input("💬 Inserisci la tua domanda qui:")
|
| 60 |
+
|
| 61 |
+
if query:
|
| 62 |
+
# 1. Embedding della query
|
| 63 |
+
query_embedding = embedder.encode([query])
|
| 64 |
+
|
| 65 |
+
# 2. Retrieval da Chroma
|
| 66 |
+
results = collection.query(query_embeddings=query_embedding, n_results=3)
|
| 67 |
+
retrieved_chunks = results["documents"][0]
|
| 68 |
+
|
| 69 |
+
# 3. Risposta con modello locale
|
| 70 |
+
response = generate_rag_response_local(query, retrieved_chunks)
|
| 71 |
+
|
| 72 |
+
# 4. Aggiorna cronologia chat
|
| 73 |
+
st.session_state.history.append(("🧑💻 Tu", query))
|
| 74 |
+
response_preview = "\n".join(response.strip().split("\n")[:2])
|
| 75 |
+
st.session_state.history.append(("🤖 RAG Bot", response_preview))
|
| 76 |
+
|
| 77 |
+
# --- OUTPUT CHAT ---
|
| 78 |
+
|
| 79 |
+
if st.session_state.history:
|
| 80 |
+
for speaker, msg in st.session_state.history:
|
| 81 |
+
st.markdown(f"**{speaker}**: {msg}")
|
| 82 |
+
|
| 83 |
+
# --- VISUALIZZA I CHUNK USATI ---
|
| 84 |
+
if query:
|
| 85 |
+
with st.expander("🔍 Mostra i documenti/chunk usati"):
|
| 86 |
+
for i, chunk in enumerate(retrieved_chunks):
|
| 87 |
+
st.markdown(f"**Chunk {i+1}**\n\n{chunk}\n\n---")
|
ingest.py
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from docling.document_converter import DocumentConverter
|
| 2 |
+
|
| 3 |
+
source = "data/insiel.pdf"
|
| 4 |
+
converter = DocumentConverter()
|
| 5 |
+
result = converter.convert(source)
|
| 6 |
+
print(result.document.export_to_markdown())
|
| 7 |
+
|
| 8 |
+
markdown_text = result.document.export_to_markdown()
|
| 9 |
+
image_count = markdown_text.count("<!-- image -->")
|
| 10 |
+
|
| 11 |
+
print(f"🔢 Immagini trovate: {image_count}")
|
rag.ipynb
ADDED
|
@@ -0,0 +1,1060 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": 1,
|
| 6 |
+
"id": "79a31d92-c664-4ed9-8e8c-07b92d2c1680",
|
| 7 |
+
"metadata": {
|
| 8 |
+
"scrolled": true
|
| 9 |
+
},
|
| 10 |
+
"outputs": [
|
| 11 |
+
{
|
| 12 |
+
"name": "stdout",
|
| 13 |
+
"output_type": "stream",
|
| 14 |
+
"text": [
|
| 15 |
+
"Requirement already satisfied: docling in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (2.30.0)\n",
|
| 16 |
+
"Requirement already satisfied: chromadb in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (1.0.5)\n",
|
| 17 |
+
"Requirement already satisfied: sentence-transformers in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (4.1.0)\n",
|
| 18 |
+
"Requirement already satisfied: beautifulsoup4<5.0.0,>=4.12.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (4.12.3)\n",
|
| 19 |
+
"Requirement already satisfied: certifi>=2024.7.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (2025.1.31)\n",
|
| 20 |
+
"Requirement already satisfied: docling-core<3.0.0,>=2.26.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling-core[chunking]<3.0.0,>=2.26.0->docling) (2.27.0)\n",
|
| 21 |
+
"Requirement already satisfied: docling-ibm-models<4.0.0,>=3.4.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (3.4.1)\n",
|
| 22 |
+
"Requirement already satisfied: docling-parse<5.0.0,>=4.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (4.0.1)\n",
|
| 23 |
+
"Requirement already satisfied: easyocr<2.0,>=1.7 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (1.7.2)\n",
|
| 24 |
+
"Requirement already satisfied: filetype<2.0.0,>=1.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (1.2.0)\n",
|
| 25 |
+
"Requirement already satisfied: huggingface_hub<1,>=0.23 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (0.30.2)\n",
|
| 26 |
+
"Requirement already satisfied: lxml<6.0.0,>=4.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (5.3.2)\n",
|
| 27 |
+
"Requirement already satisfied: marko<3.0.0,>=2.1.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (2.1.3)\n",
|
| 28 |
+
"Requirement already satisfied: openpyxl<4.0.0,>=3.1.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (3.1.5)\n",
|
| 29 |
+
"Requirement already satisfied: pandas<3.0.0,>=2.1.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (2.2.2)\n",
|
| 30 |
+
"Requirement already satisfied: pillow<12.0.0,>=10.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (10.3.0)\n",
|
| 31 |
+
"Requirement already satisfied: pluggy<2.0.0,>=1.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (1.5.0)\n",
|
| 32 |
+
"Requirement already satisfied: pydantic<3.0.0,>=2.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (2.11.3)\n",
|
| 33 |
+
"Requirement already satisfied: pydantic-settings<3.0.0,>=2.3.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (2.8.1)\n",
|
| 34 |
+
"Requirement already satisfied: pylatexenc<3.0,>=2.10 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (2.10)\n",
|
| 35 |
+
"Requirement already satisfied: pypdfium2<5.0.0,>=4.30.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (4.30.1)\n",
|
| 36 |
+
"Requirement already satisfied: python-docx<2.0.0,>=1.1.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (1.1.2)\n",
|
| 37 |
+
"Requirement already satisfied: python-pptx<2.0.0,>=1.0.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (1.0.2)\n",
|
| 38 |
+
"Requirement already satisfied: requests<3.0.0,>=2.32.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (2.32.2)\n",
|
| 39 |
+
"Requirement already satisfied: rtree<2.0.0,>=1.3.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (1.4.0)\n",
|
| 40 |
+
"Requirement already satisfied: scipy<2.0.0,>=1.6.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (1.13.1)\n",
|
| 41 |
+
"Requirement already satisfied: tqdm<5.0.0,>=4.65.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (4.66.4)\n",
|
| 42 |
+
"Requirement already satisfied: typer<0.16.0,>=0.12.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling) (0.15.2)\n",
|
| 43 |
+
"Requirement already satisfied: build>=1.0.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.2.2.post1)\n",
|
| 44 |
+
"Requirement already satisfied: chroma-hnswlib==0.7.6 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.7.6)\n",
|
| 45 |
+
"Requirement already satisfied: fastapi==0.115.9 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.115.9)\n",
|
| 46 |
+
"Requirement already satisfied: uvicorn>=0.18.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.34.1)\n",
|
| 47 |
+
"Requirement already satisfied: numpy>=1.22.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (2.2.4)\n",
|
| 48 |
+
"Requirement already satisfied: posthog>=2.4.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (3.25.0)\n",
|
| 49 |
+
"Requirement already satisfied: typing-extensions>=4.5.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (4.13.2)\n",
|
| 50 |
+
"Requirement already satisfied: onnxruntime>=1.14.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.21.0)\n",
|
| 51 |
+
"Requirement already satisfied: opentelemetry-api>=1.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.32.1)\n",
|
| 52 |
+
"Requirement already satisfied: opentelemetry-exporter-otlp-proto-grpc>=1.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.32.1)\n",
|
| 53 |
+
"Requirement already satisfied: opentelemetry-instrumentation-fastapi>=0.41b0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.53b1)\n",
|
| 54 |
+
"Requirement already satisfied: opentelemetry-sdk>=1.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.32.1)\n",
|
| 55 |
+
"Requirement already satisfied: tokenizers>=0.13.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.21.1)\n",
|
| 56 |
+
"Requirement already satisfied: pypika>=0.48.9 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.48.9)\n",
|
| 57 |
+
"Requirement already satisfied: overrides>=7.3.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (7.7.0)\n",
|
| 58 |
+
"Requirement already satisfied: importlib-resources in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (6.4.0)\n",
|
| 59 |
+
"Requirement already satisfied: grpcio>=1.58.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.70.0)\n",
|
| 60 |
+
"Requirement already satisfied: bcrypt>=4.0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (4.3.0)\n",
|
| 61 |
+
"Requirement already satisfied: kubernetes>=28.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (32.0.1)\n",
|
| 62 |
+
"Requirement already satisfied: tenacity>=8.2.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (9.1.2)\n",
|
| 63 |
+
"Requirement already satisfied: pyyaml>=6.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (6.0.1)\n",
|
| 64 |
+
"Requirement already satisfied: mmh3>=4.0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (5.1.0)\n",
|
| 65 |
+
"Requirement already satisfied: orjson>=3.9.12 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (3.10.16)\n",
|
| 66 |
+
"Requirement already satisfied: httpx>=0.27.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.27.0)\n",
|
| 67 |
+
"Requirement already satisfied: rich>=10.11.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (13.9.4)\n",
|
| 68 |
+
"Requirement already satisfied: jsonschema>=4.19.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (4.22.0)\n",
|
| 69 |
+
"Requirement already satisfied: starlette<0.46.0,>=0.40.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from fastapi==0.115.9->chromadb) (0.45.3)\n",
|
| 70 |
+
"Requirement already satisfied: transformers<5.0.0,>=4.41.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (4.51.3)\n",
|
| 71 |
+
"Requirement already satisfied: torch>=1.11.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (2.6.0)\n",
|
| 72 |
+
"Requirement already satisfied: scikit-learn in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (1.6.1)\n",
|
| 73 |
+
"Requirement already satisfied: soupsieve>1.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from beautifulsoup4<5.0.0,>=4.12.3->docling) (2.5)\n",
|
| 74 |
+
"Requirement already satisfied: packaging>=19.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from build>=1.0.3->chromadb) (24.0)\n",
|
| 75 |
+
"Requirement already satisfied: pyproject_hooks in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from build>=1.0.3->chromadb) (1.2.0)\n",
|
| 76 |
+
"Requirement already satisfied: jsonref<2.0.0,>=1.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling-core<3.0.0,>=2.26.0->docling-core[chunking]<3.0.0,>=2.26.0->docling) (1.1.0)\n",
|
| 77 |
+
"Requirement already satisfied: latex2mathml<4.0.0,>=3.77.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling-core<3.0.0,>=2.26.0->docling-core[chunking]<3.0.0,>=2.26.0->docling) (3.77.0)\n",
|
| 78 |
+
"Requirement already satisfied: tabulate<0.10.0,>=0.9.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling-core<3.0.0,>=2.26.0->docling-core[chunking]<3.0.0,>=2.26.0->docling) (0.9.0)\n",
|
| 79 |
+
"Requirement already satisfied: semchunk<3.0.0,>=2.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling-core[chunking]<3.0.0,>=2.26.0->docling) (2.2.2)\n",
|
| 80 |
+
"Requirement already satisfied: jsonlines<4.0.0,>=3.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling-ibm-models<4.0.0,>=3.4.0->docling) (3.1.0)\n",
|
| 81 |
+
"Requirement already satisfied: opencv-python-headless<5.0.0.0,>=4.6.0.66 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling-ibm-models<4.0.0,>=3.4.0->docling) (4.11.0.86)\n",
|
| 82 |
+
"Requirement already satisfied: safetensors<1,>=0.4.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from safetensors[torch]<1,>=0.4.3->docling-ibm-models<4.0.0,>=3.4.0->docling) (0.5.3)\n",
|
| 83 |
+
"Requirement already satisfied: torchvision<1,>=0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from docling-ibm-models<4.0.0,>=3.4.0->docling) (0.21.0)\n",
|
| 84 |
+
"Requirement already satisfied: scikit-image in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from easyocr<2.0,>=1.7->docling) (0.25.2)\n",
|
| 85 |
+
"Requirement already satisfied: python-bidi in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from easyocr<2.0,>=1.7->docling) (0.6.6)\n",
|
| 86 |
+
"Requirement already satisfied: Shapely in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from easyocr<2.0,>=1.7->docling) (2.1.0)\n",
|
| 87 |
+
"Requirement already satisfied: pyclipper in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from easyocr<2.0,>=1.7->docling) (1.3.0.post6)\n",
|
| 88 |
+
"Requirement already satisfied: ninja in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from easyocr<2.0,>=1.7->docling) (1.11.1.4)\n",
|
| 89 |
+
"Requirement already satisfied: anyio in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpx>=0.27.0->chromadb) (4.3.0)\n",
|
| 90 |
+
"Requirement already satisfied: httpcore==1.* in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpx>=0.27.0->chromadb) (1.0.5)\n",
|
| 91 |
+
"Requirement already satisfied: idna in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpx>=0.27.0->chromadb) (3.7)\n",
|
| 92 |
+
"Requirement already satisfied: sniffio in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpx>=0.27.0->chromadb) (1.3.1)\n",
|
| 93 |
+
"Requirement already satisfied: h11<0.15,>=0.13 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpcore==1.*->httpx>=0.27.0->chromadb) (0.14.0)\n",
|
| 94 |
+
"Requirement already satisfied: filelock in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from huggingface_hub<1,>=0.23->docling) (3.18.0)\n",
|
| 95 |
+
"Requirement already satisfied: fsspec>=2023.5.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from huggingface_hub<1,>=0.23->docling) (2025.3.2)\n",
|
| 96 |
+
"Requirement already satisfied: attrs>=22.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jsonschema>=4.19.0->chromadb) (23.2.0)\n",
|
| 97 |
+
"Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jsonschema>=4.19.0->chromadb) (2023.12.1)\n",
|
| 98 |
+
"Requirement already satisfied: referencing>=0.28.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jsonschema>=4.19.0->chromadb) (0.35.1)\n",
|
| 99 |
+
"Requirement already satisfied: rpds-py>=0.7.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jsonschema>=4.19.0->chromadb) (0.18.1)\n",
|
| 100 |
+
"Requirement already satisfied: six>=1.9.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (1.16.0)\n",
|
| 101 |
+
"Requirement already satisfied: python-dateutil>=2.5.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (2.9.0)\n",
|
| 102 |
+
"Requirement already satisfied: google-auth>=1.0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (2.39.0)\n",
|
| 103 |
+
"Requirement already satisfied: websocket-client!=0.40.0,!=0.41.*,!=0.42.*,>=0.32.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (1.8.0)\n",
|
| 104 |
+
"Requirement already satisfied: requests-oauthlib in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (2.0.0)\n",
|
| 105 |
+
"Requirement already satisfied: oauthlib>=3.2.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (3.2.2)\n",
|
| 106 |
+
"Requirement already satisfied: urllib3>=1.24.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (2.2.1)\n",
|
| 107 |
+
"Requirement already satisfied: durationpy>=0.7 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (0.9)\n",
|
| 108 |
+
"Requirement already satisfied: coloredlogs in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from onnxruntime>=1.14.1->chromadb) (15.0.1)\n",
|
| 109 |
+
"Requirement already satisfied: flatbuffers in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from onnxruntime>=1.14.1->chromadb) (25.2.10)\n",
|
| 110 |
+
"Requirement already satisfied: protobuf in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from onnxruntime>=1.14.1->chromadb) (5.29.3)\n",
|
| 111 |
+
"Requirement already satisfied: sympy in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from onnxruntime>=1.14.1->chromadb) (1.13.1)\n",
|
| 112 |
+
"Requirement already satisfied: et-xmlfile in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from openpyxl<4.0.0,>=3.1.5->docling) (2.0.0)\n",
|
| 113 |
+
"Requirement already satisfied: deprecated>=1.2.6 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-api>=1.2.0->chromadb) (1.2.18)\n",
|
| 114 |
+
"Requirement already satisfied: importlib-metadata<8.7.0,>=6.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-api>=1.2.0->chromadb) (7.1.0)\n",
|
| 115 |
+
"Requirement already satisfied: googleapis-common-protos~=1.52 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.70.0)\n",
|
| 116 |
+
"Requirement already satisfied: opentelemetry-exporter-otlp-proto-common==1.32.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.32.1)\n",
|
| 117 |
+
"Requirement already satisfied: opentelemetry-proto==1.32.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.32.1)\n",
|
| 118 |
+
"Requirement already satisfied: opentelemetry-instrumentation-asgi==0.53b1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.53b1)\n",
|
| 119 |
+
"Requirement already satisfied: opentelemetry-instrumentation==0.53b1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.53b1)\n",
|
| 120 |
+
"Requirement already satisfied: opentelemetry-semantic-conventions==0.53b1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.53b1)\n",
|
| 121 |
+
"Requirement already satisfied: opentelemetry-util-http==0.53b1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.53b1)\n",
|
| 122 |
+
"Requirement already satisfied: wrapt<2.0.0,>=1.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation==0.53b1->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (1.17.2)\n",
|
| 123 |
+
"Requirement already satisfied: asgiref~=3.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-asgi==0.53b1->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (3.8.1)\n",
|
| 124 |
+
"Requirement already satisfied: pytz>=2020.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pandas<3.0.0,>=2.1.4->docling) (2024.1)\n",
|
| 125 |
+
"Requirement already satisfied: tzdata>=2022.7 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pandas<3.0.0,>=2.1.4->docling) (2024.1)\n",
|
| 126 |
+
"Requirement already satisfied: monotonic>=1.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from posthog>=2.4.0->chromadb) (1.6)\n",
|
| 127 |
+
"Requirement already satisfied: backoff>=1.10.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from posthog>=2.4.0->chromadb) (2.2.1)\n",
|
| 128 |
+
"Requirement already satisfied: distro>=1.5.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from posthog>=2.4.0->chromadb) (1.9.0)\n",
|
| 129 |
+
"Requirement already satisfied: annotated-types>=0.6.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic<3.0.0,>=2.0.0->docling) (0.7.0)\n",
|
| 130 |
+
"Requirement already satisfied: pydantic-core==2.33.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic<3.0.0,>=2.0.0->docling) (2.33.1)\n",
|
| 131 |
+
"Requirement already satisfied: typing-inspection>=0.4.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic<3.0.0,>=2.0.0->docling) (0.4.0)\n",
|
| 132 |
+
"Requirement already satisfied: python-dotenv>=0.21.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic-settings<3.0.0,>=2.3.0->docling) (1.1.0)\n",
|
| 133 |
+
"Requirement already satisfied: XlsxWriter>=0.5.7 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from python-pptx<2.0.0,>=1.0.2->docling) (3.2.3)\n",
|
| 134 |
+
"Requirement already satisfied: charset-normalizer<4,>=2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests<3.0.0,>=2.32.2->docling) (3.3.2)\n",
|
| 135 |
+
"Requirement already satisfied: markdown-it-py>=2.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from rich>=10.11.0->chromadb) (3.0.0)\n",
|
| 136 |
+
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from rich>=10.11.0->chromadb) (2.18.0)\n",
|
| 137 |
+
"Requirement already satisfied: networkx in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from torch>=1.11.0->sentence-transformers) (3.4.2)\n",
|
| 138 |
+
"Requirement already satisfied: jinja2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from torch>=1.11.0->sentence-transformers) (3.1.4)\n",
|
| 139 |
+
"Requirement already satisfied: setuptools in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from torch>=1.11.0->sentence-transformers) (70.0.0)\n",
|
| 140 |
+
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sympy->onnxruntime>=1.14.1->chromadb) (1.3.0)\n",
|
| 141 |
+
"Requirement already satisfied: regex!=2019.12.17 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers<5.0.0,>=4.41.0->sentence-transformers) (2024.11.6)\n",
|
| 142 |
+
"Requirement already satisfied: click>=8.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from typer<0.16.0,>=0.12.5->docling) (8.1.8)\n",
|
| 143 |
+
"Requirement already satisfied: shellingham>=1.3.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from typer<0.16.0,>=0.12.5->docling) (1.5.4)\n",
|
| 144 |
+
"Requirement already satisfied: httptools>=0.6.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.6.4)\n",
|
| 145 |
+
"Requirement already satisfied: uvloop!=0.15.0,!=0.15.1,>=0.14.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.21.0)\n",
|
| 146 |
+
"Requirement already satisfied: watchfiles>=0.13 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (1.0.5)\n",
|
| 147 |
+
"Requirement already satisfied: websockets>=10.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (15.0.1)\n",
|
| 148 |
+
"Requirement already satisfied: joblib>=1.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from scikit-learn->sentence-transformers) (1.4.2)\n",
|
| 149 |
+
"Requirement already satisfied: threadpoolctl>=3.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from scikit-learn->sentence-transformers) (3.5.0)\n",
|
| 150 |
+
"Requirement already satisfied: cachetools<6.0,>=2.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (5.5.2)\n",
|
| 151 |
+
"Requirement already satisfied: pyasn1-modules>=0.2.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (0.4.2)\n",
|
| 152 |
+
"Requirement already satisfied: rsa<5,>=3.1.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (4.9.1)\n",
|
| 153 |
+
"Requirement already satisfied: zipp>=0.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from importlib-metadata<8.7.0,>=6.0->opentelemetry-api>=1.2.0->chromadb) (3.17.0)\n",
|
| 154 |
+
"Requirement already satisfied: mdurl~=0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->chromadb) (0.1.2)\n",
|
| 155 |
+
"Requirement already satisfied: mpire[dill] in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from semchunk<3.0.0,>=2.2.0->docling-core[chunking]<3.0.0,>=2.26.0->docling) (2.10.2)\n",
|
| 156 |
+
"Requirement already satisfied: humanfriendly>=9.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from coloredlogs->onnxruntime>=1.14.1->chromadb) (10.0)\n",
|
| 157 |
+
"Requirement already satisfied: MarkupSafe>=2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jinja2->torch>=1.11.0->sentence-transformers) (2.1.5)\n",
|
| 158 |
+
"Requirement already satisfied: imageio!=2.35.0,>=2.33 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from scikit-image->easyocr<2.0,>=1.7->docling) (2.37.0)\n",
|
| 159 |
+
"Requirement already satisfied: tifffile>=2022.8.12 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from scikit-image->easyocr<2.0,>=1.7->docling) (2025.3.30)\n",
|
| 160 |
+
"Requirement already satisfied: lazy-loader>=0.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from scikit-image->easyocr<2.0,>=1.7->docling) (0.4)\n",
|
| 161 |
+
"Requirement already satisfied: pyasn1<0.7.0,>=0.6.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pyasn1-modules>=0.2.1->google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (0.6.1)\n",
|
| 162 |
+
"Requirement already satisfied: multiprocess>=0.70.15 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from mpire[dill]->semchunk<3.0.0,>=2.2.0->docling-core[chunking]<3.0.0,>=2.26.0->docling) (0.70.18)\n",
|
| 163 |
+
"Requirement already satisfied: dill>=0.4.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from multiprocess>=0.70.15->mpire[dill]->semchunk<3.0.0,>=2.2.0->docling-core[chunking]<3.0.0,>=2.26.0->docling) (0.4.0)\n"
|
| 164 |
+
]
|
| 165 |
+
}
|
| 166 |
+
],
|
| 167 |
+
"source": [
|
| 168 |
+
"!pip install docling chromadb sentence-transformers"
|
| 169 |
+
]
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"cell_type": "code",
|
| 173 |
+
"execution_count": 2,
|
| 174 |
+
"id": "76269d1d-17c5-470c-a5c2-cff095cd1e53",
|
| 175 |
+
"metadata": {
|
| 176 |
+
"scrolled": true
|
| 177 |
+
},
|
| 178 |
+
"outputs": [
|
| 179 |
+
{
|
| 180 |
+
"name": "stdout",
|
| 181 |
+
"output_type": "stream",
|
| 182 |
+
"text": [
|
| 183 |
+
"Requirement already satisfied: pymupdf in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (1.25.5)\n",
|
| 184 |
+
"Requirement already satisfied: tqdm in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (4.66.4)\n",
|
| 185 |
+
"Requirement already satisfied: spacy in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (3.8.5)\n",
|
| 186 |
+
"Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (3.0.12)\n",
|
| 187 |
+
"Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (1.0.5)\n",
|
| 188 |
+
"Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (1.0.12)\n",
|
| 189 |
+
"Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (2.0.11)\n",
|
| 190 |
+
"Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (3.0.9)\n",
|
| 191 |
+
"Requirement already satisfied: thinc<8.4.0,>=8.3.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (8.3.6)\n",
|
| 192 |
+
"Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (1.1.3)\n",
|
| 193 |
+
"Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (2.5.1)\n",
|
| 194 |
+
"Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (2.0.10)\n",
|
| 195 |
+
"Requirement already satisfied: weasel<0.5.0,>=0.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (0.4.1)\n",
|
| 196 |
+
"Requirement already satisfied: typer<1.0.0,>=0.3.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (0.15.2)\n",
|
| 197 |
+
"Requirement already satisfied: numpy>=1.19.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (2.2.4)\n",
|
| 198 |
+
"Requirement already satisfied: requests<3.0.0,>=2.13.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (2.32.2)\n",
|
| 199 |
+
"Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (2.11.3)\n",
|
| 200 |
+
"Requirement already satisfied: jinja2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (3.1.4)\n",
|
| 201 |
+
"Requirement already satisfied: setuptools in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (70.0.0)\n",
|
| 202 |
+
"Requirement already satisfied: packaging>=20.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (24.0)\n",
|
| 203 |
+
"Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from spacy) (3.5.0)\n",
|
| 204 |
+
"Requirement already satisfied: language-data>=1.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from langcodes<4.0.0,>=3.2.0->spacy) (1.3.0)\n",
|
| 205 |
+
"Requirement already satisfied: annotated-types>=0.6.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (0.7.0)\n",
|
| 206 |
+
"Requirement already satisfied: pydantic-core==2.33.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (2.33.1)\n",
|
| 207 |
+
"Requirement already satisfied: typing-extensions>=4.12.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (4.13.2)\n",
|
| 208 |
+
"Requirement already satisfied: typing-inspection>=0.4.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy) (0.4.0)\n",
|
| 209 |
+
"Requirement already satisfied: charset-normalizer<4,>=2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.3.2)\n",
|
| 210 |
+
"Requirement already satisfied: idna<4,>=2.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy) (3.7)\n",
|
| 211 |
+
"Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy) (2.2.1)\n",
|
| 212 |
+
"Requirement already satisfied: certifi>=2017.4.17 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests<3.0.0,>=2.13.0->spacy) (2025.1.31)\n",
|
| 213 |
+
"Requirement already satisfied: blis<1.4.0,>=1.3.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from thinc<8.4.0,>=8.3.4->spacy) (1.3.0)\n",
|
| 214 |
+
"Requirement already satisfied: confection<1.0.0,>=0.0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from thinc<8.4.0,>=8.3.4->spacy) (0.1.5)\n",
|
| 215 |
+
"Requirement already satisfied: click>=8.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from typer<1.0.0,>=0.3.0->spacy) (8.1.8)\n",
|
| 216 |
+
"Requirement already satisfied: shellingham>=1.3.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from typer<1.0.0,>=0.3.0->spacy) (1.5.4)\n",
|
| 217 |
+
"Requirement already satisfied: rich>=10.11.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from typer<1.0.0,>=0.3.0->spacy) (13.9.4)\n",
|
| 218 |
+
"Requirement already satisfied: cloudpathlib<1.0.0,>=0.7.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from weasel<0.5.0,>=0.1.0->spacy) (0.21.0)\n",
|
| 219 |
+
"Requirement already satisfied: smart-open<8.0.0,>=5.2.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from weasel<0.5.0,>=0.1.0->spacy) (7.1.0)\n",
|
| 220 |
+
"Requirement already satisfied: MarkupSafe>=2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jinja2->spacy) (2.1.5)\n",
|
| 221 |
+
"Requirement already satisfied: marisa-trie>=1.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from language-data>=1.2->langcodes<4.0.0,>=3.2.0->spacy) (1.2.1)\n",
|
| 222 |
+
"Requirement already satisfied: markdown-it-py>=2.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy) (3.0.0)\n",
|
| 223 |
+
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy) (2.18.0)\n",
|
| 224 |
+
"Requirement already satisfied: wrapt in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from smart-open<8.0.0,>=5.2.1->weasel<0.5.0,>=0.1.0->spacy) (1.17.2)\n",
|
| 225 |
+
"Requirement already satisfied: mdurl~=0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy) (0.1.2)\n",
|
| 226 |
+
"Collecting it-core-news-sm==3.8.0\n",
|
| 227 |
+
" Using cached https://github.com/explosion/spacy-models/releases/download/it_core_news_sm-3.8.0/it_core_news_sm-3.8.0-py3-none-any.whl (13.0 MB)\n",
|
| 228 |
+
"\u001b[38;5;2m✔ Download and installation successful\u001b[0m\n",
|
| 229 |
+
"You can now load the package via spacy.load('it_core_news_sm')\n"
|
| 230 |
+
]
|
| 231 |
+
}
|
| 232 |
+
],
|
| 233 |
+
"source": [
|
| 234 |
+
"!pip install pymupdf tqdm spacy\n",
|
| 235 |
+
"!python -m spacy download it_core_news_sm"
|
| 236 |
+
]
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"cell_type": "code",
|
| 240 |
+
"execution_count": 3,
|
| 241 |
+
"id": "6c7eb59b-6ec2-45e3-8c9c-81b744f97785",
|
| 242 |
+
"metadata": {},
|
| 243 |
+
"outputs": [
|
| 244 |
+
{
|
| 245 |
+
"name": "stdout",
|
| 246 |
+
"output_type": "stream",
|
| 247 |
+
"text": [
|
| 248 |
+
"Requirement already satisfied: transformers in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (4.51.3)\n",
|
| 249 |
+
"Requirement already satisfied: filelock in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (3.18.0)\n",
|
| 250 |
+
"Requirement already satisfied: huggingface-hub<1.0,>=0.30.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (0.30.2)\n",
|
| 251 |
+
"Requirement already satisfied: numpy>=1.17 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (2.2.4)\n",
|
| 252 |
+
"Requirement already satisfied: packaging>=20.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (24.0)\n",
|
| 253 |
+
"Requirement already satisfied: pyyaml>=5.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (6.0.1)\n",
|
| 254 |
+
"Requirement already satisfied: regex!=2019.12.17 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (2024.11.6)\n",
|
| 255 |
+
"Requirement already satisfied: requests in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (2.32.2)\n",
|
| 256 |
+
"Requirement already satisfied: tokenizers<0.22,>=0.21 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (0.21.1)\n",
|
| 257 |
+
"Requirement already satisfied: safetensors>=0.4.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (0.5.3)\n",
|
| 258 |
+
"Requirement already satisfied: tqdm>=4.27 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers) (4.66.4)\n",
|
| 259 |
+
"Requirement already satisfied: fsspec>=2023.5.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from huggingface-hub<1.0,>=0.30.0->transformers) (2025.3.2)\n",
|
| 260 |
+
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from huggingface-hub<1.0,>=0.30.0->transformers) (4.13.2)\n",
|
| 261 |
+
"Requirement already satisfied: charset-normalizer<4,>=2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests->transformers) (3.3.2)\n",
|
| 262 |
+
"Requirement already satisfied: idna<4,>=2.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests->transformers) (3.7)\n",
|
| 263 |
+
"Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests->transformers) (2.2.1)\n",
|
| 264 |
+
"Requirement already satisfied: certifi>=2017.4.17 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests->transformers) (2025.1.31)\n"
|
| 265 |
+
]
|
| 266 |
+
}
|
| 267 |
+
],
|
| 268 |
+
"source": [
|
| 269 |
+
"!pip install transformers\n"
|
| 270 |
+
]
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"cell_type": "code",
|
| 274 |
+
"execution_count": 4,
|
| 275 |
+
"id": "481ee40f-059f-4feb-ae74-044413d75438",
|
| 276 |
+
"metadata": {},
|
| 277 |
+
"outputs": [
|
| 278 |
+
{
|
| 279 |
+
"data": {
|
| 280 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 281 |
+
"model_id": "ae9a7fe2333e435ead670beabaccec4f",
|
| 282 |
+
"version_major": 2,
|
| 283 |
+
"version_minor": 0
|
| 284 |
+
},
|
| 285 |
+
"text/plain": [
|
| 286 |
+
"📄 Lettura pagine PDF: 0%| | 0/66 [00:00<?, ?it/s]"
|
| 287 |
+
]
|
| 288 |
+
},
|
| 289 |
+
"metadata": {},
|
| 290 |
+
"output_type": "display_data"
|
| 291 |
+
}
|
| 292 |
+
],
|
| 293 |
+
"source": [
|
| 294 |
+
"import fitz # PyMuPDF\n",
|
| 295 |
+
"from tqdm.auto import tqdm\n",
|
| 296 |
+
"import pandas as pd\n",
|
| 297 |
+
"\n",
|
| 298 |
+
"def text_formatter(text: str) -> str:\n",
|
| 299 |
+
" # Pulizia semplice\n",
|
| 300 |
+
" import re\n",
|
| 301 |
+
" text = text.replace(\"\\n\", \" \").strip()\n",
|
| 302 |
+
" text = re.sub(r\"[ \\t]{2,}\", \" \", text)\n",
|
| 303 |
+
" text = re.sub(r\"\\.{2,}\", \" \", text) # sostituisce ... con spazio\n",
|
| 304 |
+
" text = re.sub(r\"Pagina\\s+\\d+\\s+di\\s+\\d+\", \"\", text, flags=re.IGNORECASE)\n",
|
| 305 |
+
" text = re.sub(r\"Creazione VM su Cloud INSIEL\",\"\", text)\n",
|
| 306 |
+
" text = re.sub(r\"IO_XX_00_XX ISTRUZIONE OPERATIVA 22/10/2024\", \"\",text)\n",
|
| 307 |
+
" text = re.sub(r\"IO_XX_00_XX ISTRUZIONE OPERATIVA 22/10/2024 \",\"\",text)\n",
|
| 308 |
+
" return text.strip()\n",
|
| 309 |
+
"\n",
|
| 310 |
+
"def open_and_read_pdf(pdf_path: str):\n",
|
| 311 |
+
" doc = fitz.open(pdf_path)\n",
|
| 312 |
+
" pages = []\n",
|
| 313 |
+
" for page_number, page in tqdm(enumerate(doc), total=len(doc), desc=\"📄 Lettura pagine PDF\"):\n",
|
| 314 |
+
" text = text_formatter(page.get_text())\n",
|
| 315 |
+
" pages.append({\n",
|
| 316 |
+
" \"page_number\": page_number + 1,\n",
|
| 317 |
+
" \"page_char_count\": len(text),\n",
|
| 318 |
+
" \"page_word_count\": len(text.split()),\n",
|
| 319 |
+
" \"page_token_estimate\": len(text) // 4,\n",
|
| 320 |
+
" \"text\": text\n",
|
| 321 |
+
" })\n",
|
| 322 |
+
" return pages\n",
|
| 323 |
+
"\n",
|
| 324 |
+
"pdf_path = \"data/insiel.pdf\" # Cambia se il tuo file è altrove\n",
|
| 325 |
+
"pages_and_texts = open_and_read_pdf(pdf_path)\n"
|
| 326 |
+
]
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"cell_type": "code",
|
| 330 |
+
"execution_count": 5,
|
| 331 |
+
"id": "c723bd2b-a58b-45b4-b480-fcbf4b7214ce",
|
| 332 |
+
"metadata": {},
|
| 333 |
+
"outputs": [
|
| 334 |
+
{
|
| 335 |
+
"data": {
|
| 336 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 337 |
+
"model_id": "5728eb3cb94f4eca944908b941ce7ece",
|
| 338 |
+
"version_major": 2,
|
| 339 |
+
"version_minor": 0
|
| 340 |
+
},
|
| 341 |
+
"text/plain": [
|
| 342 |
+
"✂️ Split in frasi: 0%| | 0/66 [00:00<?, ?it/s]"
|
| 343 |
+
]
|
| 344 |
+
},
|
| 345 |
+
"metadata": {},
|
| 346 |
+
"output_type": "display_data"
|
| 347 |
+
}
|
| 348 |
+
],
|
| 349 |
+
"source": [
|
| 350 |
+
"import spacy\n",
|
| 351 |
+
"nlp = spacy.load(\"it_core_news_sm\")\n",
|
| 352 |
+
"\n",
|
| 353 |
+
"# Spezza il testo di ogni pagina in frasi\n",
|
| 354 |
+
"for page in tqdm(pages_and_texts, desc=\"✂️ Split in frasi\"):\n",
|
| 355 |
+
" doc = nlp(page[\"text\"])\n",
|
| 356 |
+
" sentences = [sent.text.strip() for sent in doc.sents if sent.text.strip()]\n",
|
| 357 |
+
" page[\"sentence_chunks\"] = []\n",
|
| 358 |
+
"\n",
|
| 359 |
+
" CHUNK_SIZE = 10 # Gruppi da 5 frasi\n",
|
| 360 |
+
" for i in range(0, len(sentences), CHUNK_SIZE):\n",
|
| 361 |
+
" chunk = sentences[i:i + CHUNK_SIZE]\n",
|
| 362 |
+
" page[\"sentence_chunks\"].append(chunk)\n"
|
| 363 |
+
]
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"cell_type": "code",
|
| 367 |
+
"execution_count": 6,
|
| 368 |
+
"id": "bd7f511f-cdd9-48ae-b97b-0fb3b878bb35",
|
| 369 |
+
"metadata": {},
|
| 370 |
+
"outputs": [
|
| 371 |
+
{
|
| 372 |
+
"data": {
|
| 373 |
+
"text/plain": [
|
| 374 |
+
"{'page_number': 66,\n",
|
| 375 |
+
" 'page_char_count': 45,\n",
|
| 376 |
+
" 'page_word_count': 9,\n",
|
| 377 |
+
" 'page_token_estimate': 11,\n",
|
| 378 |
+
" 'text': 'FIGURA 88 - VMWARE NSX - CRITERIO GRUPPO 58',\n",
|
| 379 |
+
" 'sentence_chunks': [['FIGURA 88 - VMWARE NSX - CRITERIO GRUPPO 58']]}"
|
| 380 |
+
]
|
| 381 |
+
},
|
| 382 |
+
"execution_count": 6,
|
| 383 |
+
"metadata": {},
|
| 384 |
+
"output_type": "execute_result"
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"source": [
|
| 388 |
+
"pages_and_texts[65]"
|
| 389 |
+
]
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"cell_type": "code",
|
| 393 |
+
"execution_count": 7,
|
| 394 |
+
"id": "a6b65f41-9187-4667-b272-8f0117ee60b7",
|
| 395 |
+
"metadata": {},
|
| 396 |
+
"outputs": [
|
| 397 |
+
{
|
| 398 |
+
"data": {
|
| 399 |
+
"text/html": [
|
| 400 |
+
"<div>\n",
|
| 401 |
+
"<style scoped>\n",
|
| 402 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
| 403 |
+
" vertical-align: middle;\n",
|
| 404 |
+
" }\n",
|
| 405 |
+
"\n",
|
| 406 |
+
" .dataframe tbody tr th {\n",
|
| 407 |
+
" vertical-align: top;\n",
|
| 408 |
+
" }\n",
|
| 409 |
+
"\n",
|
| 410 |
+
" .dataframe thead th {\n",
|
| 411 |
+
" text-align: right;\n",
|
| 412 |
+
" }\n",
|
| 413 |
+
"</style>\n",
|
| 414 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
| 415 |
+
" <thead>\n",
|
| 416 |
+
" <tr style=\"text-align: right;\">\n",
|
| 417 |
+
" <th></th>\n",
|
| 418 |
+
" <th>page_number</th>\n",
|
| 419 |
+
" <th>page_char_count</th>\n",
|
| 420 |
+
" <th>page_word_count</th>\n",
|
| 421 |
+
" <th>page_token_estimate</th>\n",
|
| 422 |
+
" <th>text</th>\n",
|
| 423 |
+
" <th>sentence_chunks</th>\n",
|
| 424 |
+
" <th>chunk_id</th>\n",
|
| 425 |
+
" </tr>\n",
|
| 426 |
+
" </thead>\n",
|
| 427 |
+
" <tbody>\n",
|
| 428 |
+
" <tr>\n",
|
| 429 |
+
" <th>61</th>\n",
|
| 430 |
+
" <td>62</td>\n",
|
| 431 |
+
" <td>1301</td>\n",
|
| 432 |
+
" <td>173</td>\n",
|
| 433 |
+
" <td>325</td>\n",
|
| 434 |
+
" <td>7 APPENDICE 2 – NAMING CONVENTION 7.1 NOMI MAC...</td>\n",
|
| 435 |
+
" <td>[[7 APPENDICE 2 – NAMING CONVENTION 7.1 NOMI M...</td>\n",
|
| 436 |
+
" <td>61</td>\n",
|
| 437 |
+
" </tr>\n",
|
| 438 |
+
" <tr>\n",
|
| 439 |
+
" <th>62</th>\n",
|
| 440 |
+
" <td>63</td>\n",
|
| 441 |
+
" <td>344</td>\n",
|
| 442 |
+
" <td>19</td>\n",
|
| 443 |
+
" <td>86</td>\n",
|
| 444 |
+
" <td>9.3 VMWARE ARIA • HTTPS://DOCS.VMWARE.COM/IT/V...</td>\n",
|
| 445 |
+
" <td>[[9.3 VMWARE ARIA • HTTPS://DOCS.VMWARE.COM/IT...</td>\n",
|
| 446 |
+
" <td>62</td>\n",
|
| 447 |
+
" </tr>\n",
|
| 448 |
+
" <tr>\n",
|
| 449 |
+
" <th>63</th>\n",
|
| 450 |
+
" <td>64</td>\n",
|
| 451 |
+
" <td>1949</td>\n",
|
| 452 |
+
" <td>352</td>\n",
|
| 453 |
+
" <td>487</td>\n",
|
| 454 |
+
" <td>12 INDICE DELLE FIGURE FIGURA 1 - VMWARE VSPHE...</td>\n",
|
| 455 |
+
" <td>[[12 INDICE DELLE FIGURE FIGURA 1 - VMWARE VSP...</td>\n",
|
| 456 |
+
" <td>63</td>\n",
|
| 457 |
+
" </tr>\n",
|
| 458 |
+
" <tr>\n",
|
| 459 |
+
" <th>64</th>\n",
|
| 460 |
+
" <td>65</td>\n",
|
| 461 |
+
" <td>2293</td>\n",
|
| 462 |
+
" <td>446</td>\n",
|
| 463 |
+
" <td>573</td>\n",
|
| 464 |
+
" <td>FIGURA 43 – RESOURCES – MENU CONTESTUALE 30 ...</td>\n",
|
| 465 |
+
" <td>[[FIGURA 43 – RESOURCES – MENU CONTESTUALE 3...</td>\n",
|
| 466 |
+
" <td>64</td>\n",
|
| 467 |
+
" </tr>\n",
|
| 468 |
+
" <tr>\n",
|
| 469 |
+
" <th>65</th>\n",
|
| 470 |
+
" <td>66</td>\n",
|
| 471 |
+
" <td>45</td>\n",
|
| 472 |
+
" <td>9</td>\n",
|
| 473 |
+
" <td>11</td>\n",
|
| 474 |
+
" <td>FIGURA 88 - VMWARE NSX - CRITERIO GRUPPO 58</td>\n",
|
| 475 |
+
" <td>[[FIGURA 88 - VMWARE NSX - CRITERIO GRUPPO 58]]</td>\n",
|
| 476 |
+
" <td>65</td>\n",
|
| 477 |
+
" </tr>\n",
|
| 478 |
+
" </tbody>\n",
|
| 479 |
+
"</table>\n",
|
| 480 |
+
"</div>"
|
| 481 |
+
],
|
| 482 |
+
"text/plain": [
|
| 483 |
+
" page_number page_char_count page_word_count page_token_estimate \\\n",
|
| 484 |
+
"61 62 1301 173 325 \n",
|
| 485 |
+
"62 63 344 19 86 \n",
|
| 486 |
+
"63 64 1949 352 487 \n",
|
| 487 |
+
"64 65 2293 446 573 \n",
|
| 488 |
+
"65 66 45 9 11 \n",
|
| 489 |
+
"\n",
|
| 490 |
+
" text \\\n",
|
| 491 |
+
"61 7 APPENDICE 2 – NAMING CONVENTION 7.1 NOMI MAC... \n",
|
| 492 |
+
"62 9.3 VMWARE ARIA • HTTPS://DOCS.VMWARE.COM/IT/V... \n",
|
| 493 |
+
"63 12 INDICE DELLE FIGURE FIGURA 1 - VMWARE VSPHE... \n",
|
| 494 |
+
"64 FIGURA 43 – RESOURCES – MENU CONTESTUALE 30 ... \n",
|
| 495 |
+
"65 FIGURA 88 - VMWARE NSX - CRITERIO GRUPPO 58 \n",
|
| 496 |
+
"\n",
|
| 497 |
+
" sentence_chunks chunk_id \n",
|
| 498 |
+
"61 [[7 APPENDICE 2 – NAMING CONVENTION 7.1 NOMI M... 61 \n",
|
| 499 |
+
"62 [[9.3 VMWARE ARIA • HTTPS://DOCS.VMWARE.COM/IT... 62 \n",
|
| 500 |
+
"63 [[12 INDICE DELLE FIGURE FIGURA 1 - VMWARE VSP... 63 \n",
|
| 501 |
+
"64 [[FIGURA 43 – RESOURCES – MENU CONTESTUALE 3... 64 \n",
|
| 502 |
+
"65 [[FIGURA 88 - VMWARE NSX - CRITERIO GRUPPO 58]] 65 "
|
| 503 |
+
]
|
| 504 |
+
},
|
| 505 |
+
"execution_count": 7,
|
| 506 |
+
"metadata": {},
|
| 507 |
+
"output_type": "execute_result"
|
| 508 |
+
}
|
| 509 |
+
],
|
| 510 |
+
"source": [
|
| 511 |
+
"df = pd.DataFrame(pages_and_texts)\n",
|
| 512 |
+
"df[\"chunk_id\"] = df.index.astype(str)\n",
|
| 513 |
+
"\n",
|
| 514 |
+
"# Mostra i primi\n",
|
| 515 |
+
"df.tail()\n"
|
| 516 |
+
]
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"cell_type": "code",
|
| 520 |
+
"execution_count": 8,
|
| 521 |
+
"id": "b88c68ab-0fe8-407c-999d-46bccf95c95b",
|
| 522 |
+
"metadata": {},
|
| 523 |
+
"outputs": [
|
| 524 |
+
{
|
| 525 |
+
"data": {
|
| 526 |
+
"text/plain": [
|
| 527 |
+
"(66, 7)"
|
| 528 |
+
]
|
| 529 |
+
},
|
| 530 |
+
"execution_count": 8,
|
| 531 |
+
"metadata": {},
|
| 532 |
+
"output_type": "execute_result"
|
| 533 |
+
}
|
| 534 |
+
],
|
| 535 |
+
"source": [
|
| 536 |
+
"df.shape"
|
| 537 |
+
]
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"cell_type": "code",
|
| 541 |
+
"execution_count": 9,
|
| 542 |
+
"id": "8926ba95-94a7-4ae1-a217-718bc84918a7",
|
| 543 |
+
"metadata": {},
|
| 544 |
+
"outputs": [
|
| 545 |
+
{
|
| 546 |
+
"data": {
|
| 547 |
+
"text/plain": [
|
| 548 |
+
"page_number 9\n",
|
| 549 |
+
"page_char_count 9\n",
|
| 550 |
+
"page_word_count 9\n",
|
| 551 |
+
"page_token_estimate 9\n",
|
| 552 |
+
"text 9\n",
|
| 553 |
+
"sentence_chunks 9\n",
|
| 554 |
+
"chunk_id 9\n",
|
| 555 |
+
"dtype: int64"
|
| 556 |
+
]
|
| 557 |
+
},
|
| 558 |
+
"execution_count": 9,
|
| 559 |
+
"metadata": {},
|
| 560 |
+
"output_type": "execute_result"
|
| 561 |
+
}
|
| 562 |
+
],
|
| 563 |
+
"source": [
|
| 564 |
+
"df[df['page_token_estimate'] < 60].count()"
|
| 565 |
+
]
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"cell_type": "code",
|
| 569 |
+
"execution_count": 10,
|
| 570 |
+
"id": "b5c7ffd4-55a6-4486-ac70-1f5678f72046",
|
| 571 |
+
"metadata": {},
|
| 572 |
+
"outputs": [],
|
| 573 |
+
"source": [
|
| 574 |
+
"final = df[df['page_token_estimate'] > 60]"
|
| 575 |
+
]
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"cell_type": "code",
|
| 579 |
+
"execution_count": 11,
|
| 580 |
+
"id": "8e1fc3ca-a065-4c32-9acb-6cc300c7d2a1",
|
| 581 |
+
"metadata": {},
|
| 582 |
+
"outputs": [
|
| 583 |
+
{
|
| 584 |
+
"data": {
|
| 585 |
+
"text/html": [
|
| 586 |
+
"<div>\n",
|
| 587 |
+
"<style scoped>\n",
|
| 588 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
| 589 |
+
" vertical-align: middle;\n",
|
| 590 |
+
" }\n",
|
| 591 |
+
"\n",
|
| 592 |
+
" .dataframe tbody tr th {\n",
|
| 593 |
+
" vertical-align: top;\n",
|
| 594 |
+
" }\n",
|
| 595 |
+
"\n",
|
| 596 |
+
" .dataframe thead th {\n",
|
| 597 |
+
" text-align: right;\n",
|
| 598 |
+
" }\n",
|
| 599 |
+
"</style>\n",
|
| 600 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
| 601 |
+
" <thead>\n",
|
| 602 |
+
" <tr style=\"text-align: right;\">\n",
|
| 603 |
+
" <th></th>\n",
|
| 604 |
+
" <th>page_number</th>\n",
|
| 605 |
+
" <th>page_char_count</th>\n",
|
| 606 |
+
" <th>page_word_count</th>\n",
|
| 607 |
+
" <th>page_token_estimate</th>\n",
|
| 608 |
+
" </tr>\n",
|
| 609 |
+
" </thead>\n",
|
| 610 |
+
" <tbody>\n",
|
| 611 |
+
" <tr>\n",
|
| 612 |
+
" <th>count</th>\n",
|
| 613 |
+
" <td>57.00</td>\n",
|
| 614 |
+
" <td>57.00</td>\n",
|
| 615 |
+
" <td>57.00</td>\n",
|
| 616 |
+
" <td>57.00</td>\n",
|
| 617 |
+
" </tr>\n",
|
| 618 |
+
" <tr>\n",
|
| 619 |
+
" <th>mean</th>\n",
|
| 620 |
+
" <td>34.67</td>\n",
|
| 621 |
+
" <td>821.02</td>\n",
|
| 622 |
+
" <td>129.28</td>\n",
|
| 623 |
+
" <td>204.91</td>\n",
|
| 624 |
+
" </tr>\n",
|
| 625 |
+
" <tr>\n",
|
| 626 |
+
" <th>std</th>\n",
|
| 627 |
+
" <td>18.73</td>\n",
|
| 628 |
+
" <td>463.38</td>\n",
|
| 629 |
+
" <td>79.10</td>\n",
|
| 630 |
+
" <td>115.84</td>\n",
|
| 631 |
+
" </tr>\n",
|
| 632 |
+
" <tr>\n",
|
| 633 |
+
" <th>min</th>\n",
|
| 634 |
+
" <td>3.00</td>\n",
|
| 635 |
+
" <td>245.00</td>\n",
|
| 636 |
+
" <td>19.00</td>\n",
|
| 637 |
+
" <td>61.00</td>\n",
|
| 638 |
+
" </tr>\n",
|
| 639 |
+
" <tr>\n",
|
| 640 |
+
" <th>25%</th>\n",
|
| 641 |
+
" <td>19.00</td>\n",
|
| 642 |
+
" <td>457.00</td>\n",
|
| 643 |
+
" <td>71.00</td>\n",
|
| 644 |
+
" <td>114.00</td>\n",
|
| 645 |
+
" </tr>\n",
|
| 646 |
+
" <tr>\n",
|
| 647 |
+
" <th>50%</th>\n",
|
| 648 |
+
" <td>35.00</td>\n",
|
| 649 |
+
" <td>733.00</td>\n",
|
| 650 |
+
" <td>115.00</td>\n",
|
| 651 |
+
" <td>183.00</td>\n",
|
| 652 |
+
" </tr>\n",
|
| 653 |
+
" <tr>\n",
|
| 654 |
+
" <th>75%</th>\n",
|
| 655 |
+
" <td>51.00</td>\n",
|
| 656 |
+
" <td>1067.00</td>\n",
|
| 657 |
+
" <td>164.00</td>\n",
|
| 658 |
+
" <td>266.00</td>\n",
|
| 659 |
+
" </tr>\n",
|
| 660 |
+
" <tr>\n",
|
| 661 |
+
" <th>max</th>\n",
|
| 662 |
+
" <td>65.00</td>\n",
|
| 663 |
+
" <td>2293.00</td>\n",
|
| 664 |
+
" <td>446.00</td>\n",
|
| 665 |
+
" <td>573.00</td>\n",
|
| 666 |
+
" </tr>\n",
|
| 667 |
+
" </tbody>\n",
|
| 668 |
+
"</table>\n",
|
| 669 |
+
"</div>"
|
| 670 |
+
],
|
| 671 |
+
"text/plain": [
|
| 672 |
+
" page_number page_char_count page_word_count page_token_estimate\n",
|
| 673 |
+
"count 57.00 57.00 57.00 57.00\n",
|
| 674 |
+
"mean 34.67 821.02 129.28 204.91\n",
|
| 675 |
+
"std 18.73 463.38 79.10 115.84\n",
|
| 676 |
+
"min 3.00 245.00 19.00 61.00\n",
|
| 677 |
+
"25% 19.00 457.00 71.00 114.00\n",
|
| 678 |
+
"50% 35.00 733.00 115.00 183.00\n",
|
| 679 |
+
"75% 51.00 1067.00 164.00 266.00\n",
|
| 680 |
+
"max 65.00 2293.00 446.00 573.00"
|
| 681 |
+
]
|
| 682 |
+
},
|
| 683 |
+
"execution_count": 11,
|
| 684 |
+
"metadata": {},
|
| 685 |
+
"output_type": "execute_result"
|
| 686 |
+
}
|
| 687 |
+
],
|
| 688 |
+
"source": [
|
| 689 |
+
"final.describe().round(2)"
|
| 690 |
+
]
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"cell_type": "code",
|
| 694 |
+
"execution_count": 12,
|
| 695 |
+
"id": "d48140df-d520-48f7-b3c2-f4ceb3346150",
|
| 696 |
+
"metadata": {
|
| 697 |
+
"scrolled": true
|
| 698 |
+
},
|
| 699 |
+
"outputs": [
|
| 700 |
+
{
|
| 701 |
+
"name": "stdout",
|
| 702 |
+
"output_type": "stream",
|
| 703 |
+
"text": [
|
| 704 |
+
"Requirement already satisfied: sentence-transformers in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (4.1.0)\n",
|
| 705 |
+
"Requirement already satisfied: chromadb in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (1.0.5)\n",
|
| 706 |
+
"Requirement already satisfied: transformers<5.0.0,>=4.41.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (4.51.3)\n",
|
| 707 |
+
"Requirement already satisfied: tqdm in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (4.66.4)\n",
|
| 708 |
+
"Requirement already satisfied: torch>=1.11.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (2.6.0)\n",
|
| 709 |
+
"Requirement already satisfied: scikit-learn in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (1.6.1)\n",
|
| 710 |
+
"Requirement already satisfied: scipy in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (1.13.1)\n",
|
| 711 |
+
"Requirement already satisfied: huggingface-hub>=0.20.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (0.30.2)\n",
|
| 712 |
+
"Requirement already satisfied: Pillow in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (10.3.0)\n",
|
| 713 |
+
"Requirement already satisfied: typing_extensions>=4.5.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sentence-transformers) (4.13.2)\n",
|
| 714 |
+
"Requirement already satisfied: build>=1.0.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.2.2.post1)\n",
|
| 715 |
+
"Requirement already satisfied: pydantic>=1.9 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (2.11.3)\n",
|
| 716 |
+
"Requirement already satisfied: chroma-hnswlib==0.7.6 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.7.6)\n",
|
| 717 |
+
"Requirement already satisfied: fastapi==0.115.9 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.115.9)\n",
|
| 718 |
+
"Requirement already satisfied: uvicorn>=0.18.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.34.1)\n",
|
| 719 |
+
"Requirement already satisfied: numpy>=1.22.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (2.2.4)\n",
|
| 720 |
+
"Requirement already satisfied: posthog>=2.4.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (3.25.0)\n",
|
| 721 |
+
"Requirement already satisfied: onnxruntime>=1.14.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.21.0)\n",
|
| 722 |
+
"Requirement already satisfied: opentelemetry-api>=1.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.32.1)\n",
|
| 723 |
+
"Requirement already satisfied: opentelemetry-exporter-otlp-proto-grpc>=1.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.32.1)\n",
|
| 724 |
+
"Requirement already satisfied: opentelemetry-instrumentation-fastapi>=0.41b0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.53b1)\n",
|
| 725 |
+
"Requirement already satisfied: opentelemetry-sdk>=1.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.32.1)\n",
|
| 726 |
+
"Requirement already satisfied: tokenizers>=0.13.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.21.1)\n",
|
| 727 |
+
"Requirement already satisfied: pypika>=0.48.9 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.48.9)\n",
|
| 728 |
+
"Requirement already satisfied: overrides>=7.3.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (7.7.0)\n",
|
| 729 |
+
"Requirement already satisfied: importlib-resources in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (6.4.0)\n",
|
| 730 |
+
"Requirement already satisfied: grpcio>=1.58.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (1.70.0)\n",
|
| 731 |
+
"Requirement already satisfied: bcrypt>=4.0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (4.3.0)\n",
|
| 732 |
+
"Requirement already satisfied: typer>=0.9.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.15.2)\n",
|
| 733 |
+
"Requirement already satisfied: kubernetes>=28.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (32.0.1)\n",
|
| 734 |
+
"Requirement already satisfied: tenacity>=8.2.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (9.1.2)\n",
|
| 735 |
+
"Requirement already satisfied: pyyaml>=6.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (6.0.1)\n",
|
| 736 |
+
"Requirement already satisfied: mmh3>=4.0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (5.1.0)\n",
|
| 737 |
+
"Requirement already satisfied: orjson>=3.9.12 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (3.10.16)\n",
|
| 738 |
+
"Requirement already satisfied: httpx>=0.27.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (0.27.0)\n",
|
| 739 |
+
"Requirement already satisfied: rich>=10.11.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (13.9.4)\n",
|
| 740 |
+
"Requirement already satisfied: jsonschema>=4.19.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from chromadb) (4.22.0)\n",
|
| 741 |
+
"Requirement already satisfied: starlette<0.46.0,>=0.40.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from fastapi==0.115.9->chromadb) (0.45.3)\n",
|
| 742 |
+
"Requirement already satisfied: packaging>=19.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from build>=1.0.3->chromadb) (24.0)\n",
|
| 743 |
+
"Requirement already satisfied: pyproject_hooks in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from build>=1.0.3->chromadb) (1.2.0)\n",
|
| 744 |
+
"Requirement already satisfied: anyio in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpx>=0.27.0->chromadb) (4.3.0)\n",
|
| 745 |
+
"Requirement already satisfied: certifi in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpx>=0.27.0->chromadb) (2025.1.31)\n",
|
| 746 |
+
"Requirement already satisfied: httpcore==1.* in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpx>=0.27.0->chromadb) (1.0.5)\n",
|
| 747 |
+
"Requirement already satisfied: idna in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpx>=0.27.0->chromadb) (3.7)\n",
|
| 748 |
+
"Requirement already satisfied: sniffio in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpx>=0.27.0->chromadb) (1.3.1)\n",
|
| 749 |
+
"Requirement already satisfied: h11<0.15,>=0.13 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from httpcore==1.*->httpx>=0.27.0->chromadb) (0.14.0)\n",
|
| 750 |
+
"Requirement already satisfied: filelock in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from huggingface-hub>=0.20.0->sentence-transformers) (3.18.0)\n",
|
| 751 |
+
"Requirement already satisfied: fsspec>=2023.5.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from huggingface-hub>=0.20.0->sentence-transformers) (2025.3.2)\n",
|
| 752 |
+
"Requirement already satisfied: requests in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from huggingface-hub>=0.20.0->sentence-transformers) (2.32.2)\n",
|
| 753 |
+
"Requirement already satisfied: attrs>=22.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jsonschema>=4.19.0->chromadb) (23.2.0)\n",
|
| 754 |
+
"Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jsonschema>=4.19.0->chromadb) (2023.12.1)\n",
|
| 755 |
+
"Requirement already satisfied: referencing>=0.28.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jsonschema>=4.19.0->chromadb) (0.35.1)\n",
|
| 756 |
+
"Requirement already satisfied: rpds-py>=0.7.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jsonschema>=4.19.0->chromadb) (0.18.1)\n",
|
| 757 |
+
"Requirement already satisfied: six>=1.9.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (1.16.0)\n",
|
| 758 |
+
"Requirement already satisfied: python-dateutil>=2.5.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (2.9.0)\n",
|
| 759 |
+
"Requirement already satisfied: google-auth>=1.0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (2.39.0)\n",
|
| 760 |
+
"Requirement already satisfied: websocket-client!=0.40.0,!=0.41.*,!=0.42.*,>=0.32.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (1.8.0)\n",
|
| 761 |
+
"Requirement already satisfied: requests-oauthlib in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (2.0.0)\n",
|
| 762 |
+
"Requirement already satisfied: oauthlib>=3.2.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (3.2.2)\n",
|
| 763 |
+
"Requirement already satisfied: urllib3>=1.24.2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (2.2.1)\n",
|
| 764 |
+
"Requirement already satisfied: durationpy>=0.7 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from kubernetes>=28.1.0->chromadb) (0.9)\n",
|
| 765 |
+
"Requirement already satisfied: coloredlogs in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from onnxruntime>=1.14.1->chromadb) (15.0.1)\n",
|
| 766 |
+
"Requirement already satisfied: flatbuffers in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from onnxruntime>=1.14.1->chromadb) (25.2.10)\n",
|
| 767 |
+
"Requirement already satisfied: protobuf in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from onnxruntime>=1.14.1->chromadb) (5.29.3)\n",
|
| 768 |
+
"Requirement already satisfied: sympy in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from onnxruntime>=1.14.1->chromadb) (1.13.1)\n",
|
| 769 |
+
"Requirement already satisfied: deprecated>=1.2.6 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-api>=1.2.0->chromadb) (1.2.18)\n",
|
| 770 |
+
"Requirement already satisfied: importlib-metadata<8.7.0,>=6.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-api>=1.2.0->chromadb) (7.1.0)\n",
|
| 771 |
+
"Requirement already satisfied: googleapis-common-protos~=1.52 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.70.0)\n",
|
| 772 |
+
"Requirement already satisfied: opentelemetry-exporter-otlp-proto-common==1.32.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.32.1)\n",
|
| 773 |
+
"Requirement already satisfied: opentelemetry-proto==1.32.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.32.1)\n",
|
| 774 |
+
"Requirement already satisfied: opentelemetry-instrumentation-asgi==0.53b1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.53b1)\n",
|
| 775 |
+
"Requirement already satisfied: opentelemetry-instrumentation==0.53b1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.53b1)\n",
|
| 776 |
+
"Requirement already satisfied: opentelemetry-semantic-conventions==0.53b1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.53b1)\n",
|
| 777 |
+
"Requirement already satisfied: opentelemetry-util-http==0.53b1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.53b1)\n",
|
| 778 |
+
"Requirement already satisfied: wrapt<2.0.0,>=1.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation==0.53b1->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (1.17.2)\n",
|
| 779 |
+
"Requirement already satisfied: asgiref~=3.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from opentelemetry-instrumentation-asgi==0.53b1->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (3.8.1)\n",
|
| 780 |
+
"Requirement already satisfied: monotonic>=1.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from posthog>=2.4.0->chromadb) (1.6)\n",
|
| 781 |
+
"Requirement already satisfied: backoff>=1.10.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from posthog>=2.4.0->chromadb) (2.2.1)\n",
|
| 782 |
+
"Requirement already satisfied: distro>=1.5.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from posthog>=2.4.0->chromadb) (1.9.0)\n",
|
| 783 |
+
"Requirement already satisfied: annotated-types>=0.6.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic>=1.9->chromadb) (0.7.0)\n",
|
| 784 |
+
"Requirement already satisfied: pydantic-core==2.33.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic>=1.9->chromadb) (2.33.1)\n",
|
| 785 |
+
"Requirement already satisfied: typing-inspection>=0.4.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pydantic>=1.9->chromadb) (0.4.0)\n",
|
| 786 |
+
"Requirement already satisfied: markdown-it-py>=2.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from rich>=10.11.0->chromadb) (3.0.0)\n",
|
| 787 |
+
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from rich>=10.11.0->chromadb) (2.18.0)\n",
|
| 788 |
+
"Requirement already satisfied: networkx in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from torch>=1.11.0->sentence-transformers) (3.4.2)\n",
|
| 789 |
+
"Requirement already satisfied: jinja2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from torch>=1.11.0->sentence-transformers) (3.1.4)\n",
|
| 790 |
+
"Requirement already satisfied: setuptools in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from torch>=1.11.0->sentence-transformers) (70.0.0)\n",
|
| 791 |
+
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from sympy->onnxruntime>=1.14.1->chromadb) (1.3.0)\n",
|
| 792 |
+
"Requirement already satisfied: regex!=2019.12.17 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers<5.0.0,>=4.41.0->sentence-transformers) (2024.11.6)\n",
|
| 793 |
+
"Requirement already satisfied: safetensors>=0.4.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from transformers<5.0.0,>=4.41.0->sentence-transformers) (0.5.3)\n",
|
| 794 |
+
"Requirement already satisfied: click>=8.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from typer>=0.9.0->chromadb) (8.1.8)\n",
|
| 795 |
+
"Requirement already satisfied: shellingham>=1.3.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from typer>=0.9.0->chromadb) (1.5.4)\n",
|
| 796 |
+
"Requirement already satisfied: httptools>=0.6.3 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.6.4)\n",
|
| 797 |
+
"Requirement already satisfied: python-dotenv>=0.13 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (1.1.0)\n",
|
| 798 |
+
"Requirement already satisfied: uvloop!=0.15.0,!=0.15.1,>=0.14.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.21.0)\n",
|
| 799 |
+
"Requirement already satisfied: watchfiles>=0.13 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (1.0.5)\n",
|
| 800 |
+
"Requirement already satisfied: websockets>=10.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from uvicorn[standard]>=0.18.3->chromadb) (15.0.1)\n",
|
| 801 |
+
"Requirement already satisfied: joblib>=1.2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from scikit-learn->sentence-transformers) (1.4.2)\n",
|
| 802 |
+
"Requirement already satisfied: threadpoolctl>=3.1.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from scikit-learn->sentence-transformers) (3.5.0)\n",
|
| 803 |
+
"Requirement already satisfied: cachetools<6.0,>=2.0.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (5.5.2)\n",
|
| 804 |
+
"Requirement already satisfied: pyasn1-modules>=0.2.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (0.4.2)\n",
|
| 805 |
+
"Requirement already satisfied: rsa<5,>=3.1.4 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (4.9.1)\n",
|
| 806 |
+
"Requirement already satisfied: zipp>=0.5 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from importlib-metadata<8.7.0,>=6.0->opentelemetry-api>=1.2.0->chromadb) (3.17.0)\n",
|
| 807 |
+
"Requirement already satisfied: mdurl~=0.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->chromadb) (0.1.2)\n",
|
| 808 |
+
"Requirement already satisfied: charset-normalizer<4,>=2 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from requests->huggingface-hub>=0.20.0->sentence-transformers) (3.3.2)\n",
|
| 809 |
+
"Requirement already satisfied: humanfriendly>=9.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from coloredlogs->onnxruntime>=1.14.1->chromadb) (10.0)\n",
|
| 810 |
+
"Requirement already satisfied: MarkupSafe>=2.0 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from jinja2->torch>=1.11.0->sentence-transformers) (2.1.5)\n",
|
| 811 |
+
"Requirement already satisfied: pyasn1<0.7.0,>=0.6.1 in /Users/alegio98/Library/jupyterlab-desktop/jlab_server/lib/python3.12/site-packages (from pyasn1-modules>=0.2.1->google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (0.6.1)\n"
|
| 812 |
+
]
|
| 813 |
+
}
|
| 814 |
+
],
|
| 815 |
+
"source": [
|
| 816 |
+
"!pip install sentence-transformers chromadb\n"
|
| 817 |
+
]
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"cell_type": "code",
|
| 821 |
+
"execution_count": 13,
|
| 822 |
+
"id": "d80d1aec-bb7c-491e-87e5-622ffbdb29b9",
|
| 823 |
+
"metadata": {},
|
| 824 |
+
"outputs": [
|
| 825 |
+
{
|
| 826 |
+
"data": {
|
| 827 |
+
"application/vnd.jupyter.widget-view+json": {
|
| 828 |
+
"model_id": "b03b146f585f450db759a0d35e257b62",
|
| 829 |
+
"version_major": 2,
|
| 830 |
+
"version_minor": 0
|
| 831 |
+
},
|
| 832 |
+
"text/plain": [
|
| 833 |
+
"Batches: 0%| | 0/2 [00:00<?, ?it/s]"
|
| 834 |
+
]
|
| 835 |
+
},
|
| 836 |
+
"metadata": {},
|
| 837 |
+
"output_type": "display_data"
|
| 838 |
+
}
|
| 839 |
+
],
|
| 840 |
+
"source": [
|
| 841 |
+
"from sentence_transformers import SentenceTransformer\n",
|
| 842 |
+
"from tqdm.notebook import tqdm\n",
|
| 843 |
+
"\n",
|
| 844 |
+
"embedding_model = SentenceTransformer(\"sentence-transformers/distiluse-base-multilingual-cased-v1\")\n",
|
| 845 |
+
"\n",
|
| 846 |
+
"texts = final[\"text\"].tolist()\n",
|
| 847 |
+
"chunk_ids = final[\"chunk_id\"].tolist()\n",
|
| 848 |
+
"metadatas = [{\"page\": int(p)} for p in final[\"page_number\"]]\n",
|
| 849 |
+
"\n",
|
| 850 |
+
"embeddings = embedding_model.encode(texts, show_progress_bar=True)\n"
|
| 851 |
+
]
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"cell_type": "code",
|
| 855 |
+
"execution_count": 14,
|
| 856 |
+
"id": "27cb5630-e180-4c66-9c02-05b797e14c6c",
|
| 857 |
+
"metadata": {},
|
| 858 |
+
"outputs": [],
|
| 859 |
+
"source": [
|
| 860 |
+
"import chromadb\n",
|
| 861 |
+
"\n",
|
| 862 |
+
"# nuovo client\n",
|
| 863 |
+
"client = chromadb.PersistentClient(path=\"./vectorstore\")\n",
|
| 864 |
+
"\n",
|
| 865 |
+
"# collection\n",
|
| 866 |
+
"collection = client.get_or_create_collection(\"insiel_chunks\")\n",
|
| 867 |
+
"\n",
|
| 868 |
+
"# aggiunta\n",
|
| 869 |
+
"collection.add(\n",
|
| 870 |
+
" documents=texts,\n",
|
| 871 |
+
" embeddings=embeddings.tolist(),\n",
|
| 872 |
+
" metadatas=metadatas,\n",
|
| 873 |
+
" ids=chunk_ids\n",
|
| 874 |
+
")"
|
| 875 |
+
]
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"cell_type": "code",
|
| 879 |
+
"execution_count": 16,
|
| 880 |
+
"id": "6d1f5c63-7d31-49a3-bb15-9d681a22b47e",
|
| 881 |
+
"metadata": {},
|
| 882 |
+
"outputs": [
|
| 883 |
+
{
|
| 884 |
+
"name": "stdin",
|
| 885 |
+
"output_type": "stream",
|
| 886 |
+
"text": [
|
| 887 |
+
"Domanda: ciao\n"
|
| 888 |
+
]
|
| 889 |
+
}
|
| 890 |
+
],
|
| 891 |
+
"source": [
|
| 892 |
+
"query = input(\"Domanda: \")\n",
|
| 893 |
+
"query_embedding = embedding_model.encode([query])\n",
|
| 894 |
+
"\n",
|
| 895 |
+
"results = collection.query(\n",
|
| 896 |
+
" query_embeddings=query_embedding,\n",
|
| 897 |
+
" n_results=3 # puoi aumentare a 5, 10, ecc.\n",
|
| 898 |
+
")"
|
| 899 |
+
]
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"cell_type": "code",
|
| 903 |
+
"execution_count": 17,
|
| 904 |
+
"id": "1c5dde05-99a5-4ee9-ad9a-112888745464",
|
| 905 |
+
"metadata": {},
|
| 906 |
+
"outputs": [
|
| 907 |
+
{
|
| 908 |
+
"name": "stdout",
|
| 909 |
+
"output_type": "stream",
|
| 910 |
+
"text": [
|
| 911 |
+
"\n",
|
| 912 |
+
"🔹 RISULTATO 1 (pagina 41):\n",
|
| 913 |
+
"o 17 macchine virtuali (vedi PAR. 5.4.1.1.4.4). o 0 profili di accesso a Livello 7 (vedi PAR. 5.4.1.1.4.3). o 2 sevizi (vedi PAR 5.4.1.1.4.1) o 6 profili contesto (vedi PAR. 5.4.1.1.4.3). 5.4.1.1.2.2 AVVISI Nel tab ‘Avvisi’ sono presenti due sotto tab: • Avvisi • Definizione avvisi Figura 60 - VMWare NSX – Home – Avvisi Figura 61 - VMWare NSX – Home – Definizione avvisi...\n",
|
| 914 |
+
"---\n",
|
| 915 |
+
"\n",
|
| 916 |
+
"🔹 RISULTATO 2 (pagina 60):\n",
|
| 917 |
+
"5.5.3.1.1 MICROSOFT WINDOWS SERVER 5.5.3.1.2 LINUX 5.5.3.2 AGGIUNTA A DOMINIO 5.5.3.3 ESPANSIONE DISCO DI SISTEMA 5.5.3.4 AGGIORNAMENTO SISTEMA OPERATIVO 5.5.3.4.1 VERIFICA SU CONSOLE WSUS 5.5.3.4.2 AGGIORNAMENTO E PATCHING 5.5.3.5 INSTALLAZIONE ANTIVIRUS 5.5.3.5.1 VERIFICA FUNZIONAMENTO SU CONSOLE ANTIVIRUS...\n",
|
| 918 |
+
"---\n",
|
| 919 |
+
"\n",
|
| 920 |
+
"🔹 RISULTATO 3 (pagina 3):\n",
|
| 921 |
+
"INDICE 1 SCOPO 5 2 AMBITO DI APPLICAZIONE 5 3 ACRONIMI E DEFINIZIONI 5 4 RESPONSABILITA’ 5 5 MODALITÀ ESECUTIVE 6 5.1 CONFIGURAZIONE DELL’INFRASTRUTTURA 6 5.1.1 VMWARE VSPHERE 6 5.1.2 VMWARE NSX 7 5.1.3 VMWARE ARIA 8 5.2 IMPLEMENTAZIONE DELL’INFRASTRUTTURA 9 5.2.1 LOCALIZZAZIONE 9 5.2.2 CONNETTIVITA’ DI RETE 9 5.2.2.1 CONNETTIVITA’ FISICA 9 5.2.2.2 CONNETTIVITA’ LOGICA 9 5.3 CLOUD INSIEL 11 5.3.1 ACCESSO AL CLOUD INSIEL 11 5.3.1.1 LOGIN 11 5.3.1.2 RESET PASSWORD ...\n",
|
| 922 |
+
"---\n"
|
| 923 |
+
]
|
| 924 |
+
}
|
| 925 |
+
],
|
| 926 |
+
"source": [
|
| 927 |
+
"for i, (doc, meta) in enumerate(zip(results[\"documents\"][0], results[\"metadatas\"][0])):\n",
|
| 928 |
+
" print(f\"\\n🔹 RISULTATO {i+1} (pagina {meta['page']}):\")\n",
|
| 929 |
+
" print(doc[:500] + \"...\\n---\")\n"
|
| 930 |
+
]
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"cell_type": "code",
|
| 934 |
+
"execution_count": 18,
|
| 935 |
+
"id": "065512aa-94b1-4d68-82c9-3ab3b35fb534",
|
| 936 |
+
"metadata": {},
|
| 937 |
+
"outputs": [
|
| 938 |
+
{
|
| 939 |
+
"name": "stderr",
|
| 940 |
+
"output_type": "stream",
|
| 941 |
+
"text": [
|
| 942 |
+
"Device set to use cpu\n"
|
| 943 |
+
]
|
| 944 |
+
}
|
| 945 |
+
],
|
| 946 |
+
"source": [
|
| 947 |
+
"import torch\n",
|
| 948 |
+
"from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline\n",
|
| 949 |
+
"\n",
|
| 950 |
+
"model_id = \"TinyLlama/TinyLlama-1.1B-Chat-v1.0\"\n",
|
| 951 |
+
"\n",
|
| 952 |
+
"tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
|
| 953 |
+
"model = AutoModelForCausalLM.from_pretrained(model_id).to(torch.device(\"cpu\"))\n",
|
| 954 |
+
"\n",
|
| 955 |
+
"rag_chat = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=200, device=-1)\n"
|
| 956 |
+
]
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"cell_type": "code",
|
| 960 |
+
"execution_count": null,
|
| 961 |
+
"id": "ef436727-c660-4943-be68-f3c02d998a91",
|
| 962 |
+
"metadata": {},
|
| 963 |
+
"outputs": [],
|
| 964 |
+
"source": [
|
| 965 |
+
"def generate_rag_response_local(query, retrieved_chunks):\n",
|
| 966 |
+
" context = \"\\n\\n\".join(retrieved_chunks)\n",
|
| 967 |
+
" \n",
|
| 968 |
+
" prompt = f\"\"\"[INST] Usa solo le informazioni fornite nel contesto qui sotto per rispondere alla domanda, la risposta deve finire sempre con un punto. \n",
|
| 969 |
+
"Se la risposta non è presente, di' chiaramente che non è specificato nel documento.\n",
|
| 970 |
+
"\n",
|
| 971 |
+
"Contesto:\n",
|
| 972 |
+
"{context}\n",
|
| 973 |
+
"\n",
|
| 974 |
+
"Domanda: {query}\n",
|
| 975 |
+
"Risposta: [/INST]\n",
|
| 976 |
+
"\"\"\"\n",
|
| 977 |
+
" result = rag_chat(prompt)[0][\"generated_text\"]\n",
|
| 978 |
+
" return result.split(\"Risposta:\")[-1].strip()\n"
|
| 979 |
+
]
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"cell_type": "code",
|
| 983 |
+
"execution_count": null,
|
| 984 |
+
"id": "bde08911-05ae-4c87-8892-2747b87d89fc",
|
| 985 |
+
"metadata": {},
|
| 986 |
+
"outputs": [],
|
| 987 |
+
"source": [
|
| 988 |
+
"# 🧠 Inserisci la domanda\n",
|
| 989 |
+
"query = input(\"Domanda: \")\n",
|
| 990 |
+
"\n",
|
| 991 |
+
"# 🔎 Ottieni l'embedding della query (usa sentence-transformers, NON il modello generativo!)\n",
|
| 992 |
+
"query_embedding = embedding_model.encode([query]) \n",
|
| 993 |
+
"\n",
|
| 994 |
+
"# 🔍 Retrieval dei chunk più simili da Chroma\n",
|
| 995 |
+
"results = collection.query(\n",
|
| 996 |
+
" query_embeddings=query_embedding,\n",
|
| 997 |
+
" n_results=3\n",
|
| 998 |
+
")\n",
|
| 999 |
+
"\n",
|
| 1000 |
+
"# 🧱 Estrai i chunk di contesto\n",
|
| 1001 |
+
"retrieved_chunks = results[\"documents\"][0]\n",
|
| 1002 |
+
"\n",
|
| 1003 |
+
"# 🤖 Genera la risposta usando il modello open-source locale\n",
|
| 1004 |
+
"response = generate_rag_response_local(query, retrieved_chunks)\n",
|
| 1005 |
+
"\n",
|
| 1006 |
+
"# 🖨️ Mostra la risposta\n",
|
| 1007 |
+
"print(\"🤖 Risposta:\\n\", response)\n"
|
| 1008 |
+
]
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"cell_type": "code",
|
| 1012 |
+
"execution_count": null,
|
| 1013 |
+
"id": "12423be3-2773-4246-bcc8-d98634638cc5",
|
| 1014 |
+
"metadata": {},
|
| 1015 |
+
"outputs": [],
|
| 1016 |
+
"source": [
|
| 1017 |
+
"retrieved_chunks\n"
|
| 1018 |
+
]
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"cell_type": "code",
|
| 1022 |
+
"execution_count": null,
|
| 1023 |
+
"id": "88f9cd0b-c6b7-491e-8be3-6f76eb2b435d",
|
| 1024 |
+
"metadata": {},
|
| 1025 |
+
"outputs": [],
|
| 1026 |
+
"source": [
|
| 1027 |
+
"results"
|
| 1028 |
+
]
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"cell_type": "code",
|
| 1032 |
+
"execution_count": null,
|
| 1033 |
+
"id": "b8b383a1-6630-488b-908c-70da2975ca8a",
|
| 1034 |
+
"metadata": {},
|
| 1035 |
+
"outputs": [],
|
| 1036 |
+
"source": []
|
| 1037 |
+
}
|
| 1038 |
+
],
|
| 1039 |
+
"metadata": {
|
| 1040 |
+
"kernelspec": {
|
| 1041 |
+
"display_name": "Python 3 (ipykernel)",
|
| 1042 |
+
"language": "python",
|
| 1043 |
+
"name": "python3"
|
| 1044 |
+
},
|
| 1045 |
+
"language_info": {
|
| 1046 |
+
"codemirror_mode": {
|
| 1047 |
+
"name": "ipython",
|
| 1048 |
+
"version": 3
|
| 1049 |
+
},
|
| 1050 |
+
"file_extension": ".py",
|
| 1051 |
+
"mimetype": "text/x-python",
|
| 1052 |
+
"name": "python",
|
| 1053 |
+
"nbconvert_exporter": "python",
|
| 1054 |
+
"pygments_lexer": "ipython3",
|
| 1055 |
+
"version": "3.12.3"
|
| 1056 |
+
}
|
| 1057 |
+
},
|
| 1058 |
+
"nbformat": 4,
|
| 1059 |
+
"nbformat_minor": 5
|
| 1060 |
+
}
|
requirements.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
streamlit
|
| 2 |
+
chromadb>=0.4.24
|
| 3 |
+
sentence-transformers
|
| 4 |
+
transformers
|
| 5 |
+
torch
|
vectorstore/c96ac4dc-364a-4b68-9ffb-04f2ea25be4c/data_level0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee9bc52aeaf009739c1ee5c089e16c91fe21ba038b7858036eee75f7ca16271d
|
| 3 |
+
size 21880000
|
vectorstore/c96ac4dc-364a-4b68-9ffb-04f2ea25be4c/header.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb475ecb14b0f4c919eb830b06969df3dec9fc47060a7f02514eb72a351cf4a
|
| 3 |
+
size 100
|
vectorstore/c96ac4dc-364a-4b68-9ffb-04f2ea25be4c/length.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7e2dcff542de95352682dc186432e98f0188084896773f1973276b0577d5305
|
| 3 |
+
size 40000
|
vectorstore/c96ac4dc-364a-4b68-9ffb-04f2ea25be4c/link_lists.bin
ADDED
|
File without changes
|