File size: 5,446 Bytes
6e43359
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
#!/usr/bin/env python3
import os
import glob
from typing import List
from dotenv import load_dotenv
from multiprocessing import Pool
from tqdm import tqdm

from langchain.document_loaders import (
    CSVLoader,
    EverNoteLoader,
    PyMuPDFLoader,
    TextLoader,
    UnstructuredEmailLoader,
    UnstructuredEPubLoader,
    UnstructuredHTMLLoader,
    UnstructuredMarkdownLoader,
    UnstructuredODTLoader,
    UnstructuredPowerPointLoader,
    UnstructuredWordDocumentLoader,
    PyPDFLoader
)

from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.docstore.document import Document

if not load_dotenv():
    print("Could not load .env file or it is empty. Please check if it exists and is readable.")
    exit(1)

from constants import CHROMA_SETTINGS
import chromadb

# Load environment variables
persist_directory = os.environ.get('PERSIST_DIRECTORY')
source_directory = os.environ.get('SOURCE_DIRECTORY', 'source_documents')
embeddings_model_name = os.environ.get('EMBEDDINGS_MODEL_NAME')
chunk_size = 500
chunk_overlap = 100

# Map file extensions to document loaders and their arguments
LOADER_MAPPING = {
    ".csv": (CSVLoader, {}),
    # ".docx": (Docx2txtLoader, {}),
    ".doc": (UnstructuredWordDocumentLoader, {}),
    ".docx": (UnstructuredWordDocumentLoader, {}),
    ".enex": (EverNoteLoader, {}),
    # ".eml": (MyElmLoader, {}),
    ".epub": (UnstructuredEPubLoader, {}),
    ".html": (UnstructuredHTMLLoader, {}),
    ".md": (UnstructuredMarkdownLoader, {}),
    ".odt": (UnstructuredODTLoader, {}),
    # ".pdf": (PyMuPDFLoader, {}),
    ".pdf": (PyPDFLoader, {}),
    ".ppt": (UnstructuredPowerPointLoader, {}),
    ".pptx": (UnstructuredPowerPointLoader, {}),
    ".txt": (TextLoader, {"encoding": "utf8"}),
    # Add more mappings for other file extensions and loaders as needed
}


def load_single_document(file_path: str) -> List[Document]:
    ext = "." + file_path.rsplit(".", 1)[-1].lower()
    if ext in LOADER_MAPPING:
        loader_class, loader_args = LOADER_MAPPING[ext]
        loader = loader_class(file_path, **loader_args)
        return loader.load()

    raise ValueError(f"Unsupported file extension '{ext}'")

def load_documents(source_dir: str, ignored_files: List[str] = []) -> List[Document]:
    """
    Loads all documents from the source documents directory, ignoring specified files
    """
    all_files = []
    for ext in LOADER_MAPPING:
        all_files.extend(
            glob.glob(os.path.join(source_dir, f"**/*{ext.lower()}"), recursive=True)
        )
        all_files.extend(
            glob.glob(os.path.join(source_dir, f"**/*{ext.upper()}"), recursive=True)
        )
    filtered_files = [file_path for file_path in all_files if file_path not in ignored_files]

    with Pool(processes=os.cpu_count()) as pool:
        results = []
        with tqdm(total=len(filtered_files), desc='Loading new documents', ncols=80) as pbar:
            for i, docs in enumerate(pool.imap_unordered(load_single_document, filtered_files)):
                results.extend(docs)
                pbar.update()

    return results

def process_documents(ignored_files: List[str] = []) -> List[Document]:
    """
    Load documents and split in chunks
    """
    print(f"Loading documents from {source_directory}")
    documents = load_documents(source_directory, ignored_files)
    if not documents:
        print("No new documents to load")
        exit(0)
    print(f"Loaded {len(documents)} new documents from {source_directory}")
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
    texts = text_splitter.split_documents(documents)
    print(f"Split into {len(texts)} chunks of text (max. {chunk_size} tokens each)")
    return texts

def does_vectorstore_exist(persist_directory: str, embeddings: HuggingFaceEmbeddings) -> bool:
    """
    Checks if vectorstore exists
    """
    db = Chroma(persist_directory=persist_directory, embedding_function=embeddings)
    if not db.get()['documents']:
        return False
    return True

def main():
    # Create embeddings
    embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
    # Chroma client
    chroma_client = chromadb.PersistentClient(settings=CHROMA_SETTINGS , path=persist_directory)

    if does_vectorstore_exist(persist_directory, embeddings):
        # Update and store locally vectorstore
        print(f"Appending to existing vectorstore at {persist_directory}")
        db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS, client=chroma_client)
        collection = db.get()
        texts = process_documents([metadata['source'] for metadata in collection['metadatas']])
        print(f"Creating embeddings. May take some minutes...")
        db.add_documents(texts)
    else:
        # Create and store locally vectorstore
        print("Creating new vectorstore")
        texts = process_documents()
        print(f"Creating embeddings. May take some minutes...")
        db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory, client_settings=CHROMA_SETTINGS, client=chroma_client)
    db.persist()
    db = None

    print(f"Ingestion complete! You can now run app.py to query your documents")


if __name__ == "__main__":
    main()