add google hostory api
This commit is contained in:
yichuan520030910320
234
examples/google_history_reader_leann.py
Normal file
234
examples/google_history_reader_leann.py
Normal file
@@ -0,0 +1,234 @@
|
||||
import os
|
||||
import asyncio
|
||||
import dotenv
|
||||
from pathlib import Path
|
||||
from typing import List, Any
|
||||
from leann.api import LeannBuilder, LeannSearcher, LeannChat
|
||||
from llama_index.core.node_parser import SentenceSplitter
|
||||
|
||||
dotenv.load_dotenv()
|
||||
|
||||
def create_leann_index_from_multiple_chrome_profiles(profile_dirs: List[Path], index_path: str = "chrome_history_index.leann", max_count: int = -1):
|
||||
"""
|
||||
Create LEANN index from multiple Chrome profile data sources.
|
||||
|
||||
Args:
|
||||
profile_dirs: List of Path objects pointing to Chrome profile directories
|
||||
index_path: Path to save the LEANN index
|
||||
max_count: Maximum number of history entries to process per profile
|
||||
"""
|
||||
print("Creating LEANN index from multiple Chrome profile data sources...")
|
||||
|
||||
# Load documents using ChromeHistoryReader from history_data
|
||||
from history_data.history import ChromeHistoryReader
|
||||
reader = ChromeHistoryReader()
|
||||
|
||||
INDEX_DIR = Path(index_path).parent
|
||||
|
||||
if not INDEX_DIR.exists():
|
||||
print(f"--- Index directory not found, building new index ---")
|
||||
all_documents = []
|
||||
total_processed = 0
|
||||
|
||||
# Process each Chrome profile directory
|
||||
for i, profile_dir in enumerate(profile_dirs):
|
||||
print(f"\nProcessing Chrome profile {i+1}/{len(profile_dirs)}: {profile_dir}")
|
||||
|
||||
try:
|
||||
documents = reader.load_data(
|
||||
chrome_profile_path=str(profile_dir),
|
||||
max_count=max_count
|
||||
)
|
||||
if documents:
|
||||
print(f"Loaded {len(documents)} history documents from {profile_dir}")
|
||||
all_documents.extend(documents)
|
||||
total_processed += len(documents)
|
||||
|
||||
# Check if we've reached the max count
|
||||
if max_count > 0 and total_processed >= max_count:
|
||||
print(f"Reached max count of {max_count} documents")
|
||||
break
|
||||
else:
|
||||
print(f"No documents loaded from {profile_dir}")
|
||||
except Exception as e:
|
||||
print(f"Error processing {profile_dir}: {e}")
|
||||
continue
|
||||
|
||||
if not all_documents:
|
||||
print("No documents loaded from any source. Exiting.")
|
||||
return None
|
||||
|
||||
print(f"\nTotal loaded {len(all_documents)} history documents from {len(profile_dirs)} profiles")
|
||||
|
||||
# Create text splitter with 256 chunk size
|
||||
text_splitter = SentenceSplitter(chunk_size=256, chunk_overlap=25)
|
||||
|
||||
# Convert Documents to text strings and chunk them
|
||||
all_texts = []
|
||||
for doc in all_documents:
|
||||
# Split the document into chunks
|
||||
nodes = text_splitter.get_nodes_from_documents([doc])
|
||||
for node in nodes:
|
||||
all_texts.append(node.get_content())
|
||||
|
||||
print(f"Created {len(all_texts)} text chunks from {len(all_documents)} documents")
|
||||
|
||||
# Create LEANN index directory
|
||||
print(f"--- Index directory not found, building new index ---")
|
||||
INDEX_DIR.mkdir(exist_ok=True)
|
||||
|
||||
print(f"--- Building new LEANN index ---")
|
||||
|
||||
print(f"\n[PHASE 1] Building Leann index...")
|
||||
|
||||
# Use HNSW backend for better macOS compatibility
|
||||
builder = LeannBuilder(
|
||||
backend_name="hnsw",
|
||||
embedding_model="facebook/contriever",
|
||||
graph_degree=32,
|
||||
complexity=64,
|
||||
is_compact=True,
|
||||
is_recompute=True,
|
||||
num_threads=1 # Force single-threaded mode
|
||||
)
|
||||
|
||||
print(f"Adding {len(all_texts)} history chunks to index...")
|
||||
for chunk_text in all_texts:
|
||||
builder.add_text(chunk_text)
|
||||
|
||||
builder.build_index(index_path)
|
||||
print(f"\nLEANN index built at {index_path}!")
|
||||
else:
|
||||
print(f"--- Using existing index at {INDEX_DIR} ---")
|
||||
|
||||
return index_path
|
||||
|
||||
def create_leann_index(profile_path: str = None, index_path: str = "chrome_history_index.leann", max_count: int = 1000):
|
||||
"""
|
||||
Create LEANN index from Chrome history data.
|
||||
|
||||
Args:
|
||||
profile_path: Path to the Chrome profile directory (optional, uses default if None)
|
||||
index_path: Path to save the LEANN index
|
||||
max_count: Maximum number of history entries to process
|
||||
"""
|
||||
print("Creating LEANN index from Chrome history data...")
|
||||
INDEX_DIR = Path(index_path).parent
|
||||
|
||||
if not INDEX_DIR.exists():
|
||||
print(f"--- Index directory not found, building new index ---")
|
||||
INDEX_DIR.mkdir(exist_ok=True)
|
||||
|
||||
print(f"--- Building new LEANN index ---")
|
||||
|
||||
print(f"\n[PHASE 1] Building Leann index...")
|
||||
|
||||
# Load documents using ChromeHistoryReader from history_data
|
||||
from history_data.history import ChromeHistoryReader
|
||||
reader = ChromeHistoryReader()
|
||||
|
||||
documents = reader.load_data(
|
||||
chrome_profile_path=profile_path,
|
||||
max_count=max_count
|
||||
)
|
||||
|
||||
if not documents:
|
||||
print("No documents loaded. Exiting.")
|
||||
return None
|
||||
|
||||
print(f"Loaded {len(documents)} history documents")
|
||||
|
||||
# Create text splitter with 256 chunk size
|
||||
text_splitter = SentenceSplitter(chunk_size=256, chunk_overlap=25)
|
||||
|
||||
# Convert Documents to text strings and chunk them
|
||||
all_texts = []
|
||||
for doc in documents:
|
||||
# Split the document into chunks
|
||||
nodes = text_splitter.get_nodes_from_documents([doc])
|
||||
for node in nodes:
|
||||
all_texts.append(node.get_content())
|
||||
|
||||
print(f"Created {len(all_texts)} text chunks from {len(documents)} documents")
|
||||
|
||||
# Create LEANN index directory
|
||||
print(f"--- Index directory not found, building new index ---")
|
||||
INDEX_DIR.mkdir(exist_ok=True)
|
||||
|
||||
print(f"--- Building new LEANN index ---")
|
||||
|
||||
print(f"\n[PHASE 1] Building Leann index...")
|
||||
|
||||
# Use HNSW backend for better macOS compatibility
|
||||
builder = LeannBuilder(
|
||||
backend_name="hnsw",
|
||||
embedding_model="facebook/contriever",
|
||||
graph_degree=32,
|
||||
complexity=64,
|
||||
is_compact=True,
|
||||
is_recompute=True,
|
||||
num_threads=1 # Force single-threaded mode
|
||||
)
|
||||
|
||||
print(f"Adding {len(all_texts)} history chunks to index...")
|
||||
for chunk_text in all_texts:
|
||||
builder.add_text(chunk_text)
|
||||
|
||||
builder.build_index(index_path)
|
||||
print(f"\nLEANN index built at {index_path}!")
|
||||
else:
|
||||
print(f"--- Using existing index at {INDEX_DIR} ---")
|
||||
|
||||
return index_path
|
||||
|
||||
async def query_leann_index(index_path: str, query: str):
|
||||
"""
|
||||
Query the LEANN index.
|
||||
|
||||
Args:
|
||||
index_path: Path to the LEANN index
|
||||
query: The query string
|
||||
"""
|
||||
print(f"\n[PHASE 2] Starting Leann chat session...")
|
||||
chat = LeannChat(index_path=index_path)
|
||||
|
||||
print(f"You: {query}")
|
||||
chat_response = chat.ask(
|
||||
query,
|
||||
top_k=5,
|
||||
recompute_beighbor_embeddings=True,
|
||||
complexity=128,
|
||||
beam_width=1
|
||||
)
|
||||
print(f"Leann: {chat_response}")
|
||||
|
||||
async def main():
|
||||
# Default Chrome profile path
|
||||
default_chrome_profile = os.path.expanduser("~/Library/Application Support/Google/Chrome/Default")
|
||||
|
||||
INDEX_DIR = Path("./chrome_history_index_leann")
|
||||
INDEX_PATH = str(INDEX_DIR / "chrome_history.leann")
|
||||
|
||||
# Find all Chrome profile directories
|
||||
from history_data.history import ChromeHistoryReader
|
||||
profile_dirs = ChromeHistoryReader.find_chrome_profiles()
|
||||
|
||||
if not profile_dirs:
|
||||
print("No Chrome profiles found. Exiting.")
|
||||
return
|
||||
|
||||
# Create or load the LEANN index from all sources
|
||||
index_path = create_leann_index_from_multiple_chrome_profiles(profile_dirs, INDEX_PATH)
|
||||
|
||||
if index_path:
|
||||
# Example queries
|
||||
queries = [
|
||||
"What websites did I visit about machine learning?",
|
||||
]
|
||||
|
||||
for query in queries:
|
||||
print("\n" + "="*60)
|
||||
await query_leann_index(index_path, query)
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
Reference in New Issue
Block a user