From 49e6e09d6360fafcb759f5f9fafd878784965109 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=94=D0=B0=D0=BD=D0=B8=D0=B8=D0=BB=20=D0=92=D0=B8=D0=BA?=
 =?UTF-8?q?=D1=82=D0=BE=D1=80=D0=BE=D0=B2?= <mr.face2002@gmail.com>
Date: Thu, 2 Jul 2026 09:38:31 +0000
Subject: [PATCH] =?UTF-8?q?fix:=20load=5Fdocs.py=20=E2=80=94=20=D0=90?=
 =?UTF-8?q?=D0=B3=D0=B5=D0=BD=D1=82=20=D1=81=20RAG-=D0=BF=D0=B0=D0=BC?=
 =?UTF-8?q?=D1=8F=D1=82=D1=8C=D1=8E?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 load_docs.py | 60 +++++++++++++---------------------------------------
 1 file changed, 15 insertions(+), 45 deletions(-)

diff --git a/load_docs.py b/load_docs.py
index 9f98af6..d690a62 100644
--- a/load_docs.py
+++ b/load_docs.py
@@ -1,49 +1,19 @@
-import os
-import argparse
-from dotenv import load_dotenv
-from langchain_openai import OpenAIEmbeddings
-from langchain_qdrant import QdrantVectorStore
-from langchain_text_splitters import RecursiveCharacterTextSplitter
+import sys
+from pathlib import Path
+
+from utils import splitter, vector_store
 from langchain_core.documents import Document
-from qdrant_client import QdrantClient
 
-# Загрузка переменных окружения
-load_dotenv()
-
-# Инициализация эмбеддингов
-embeddings = OpenAIEmbeddings(
-    model="text-embedding-3-small",
-    base_url="https://openrouter.ai/api/v1",
-    api_key=os.getenv("OPENAI_API_KEY"),
-)
-
-# Инициализация Qdrant
-client = QdrantClient(url="http://localhost:6333")
-collection_name = "knowledge_base"
-vector_store = QdrantVectorStore(
-    client=client,
-    collection_name=collection_name,
-    embeddings=embeddings,
-)
-
-# Чанкинг
-splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-
-def load_directory(dir_path: str):
-    """Загружает все .txt файлы из директории в векторную базу."""
-    for root, dirs, files in os.walk(dir_path):
-        for file in files:
-            if file.lower().endswith(".txt"):
-                path = os.path.join(root, file)
-                with open(path, "r", encoding="utf-8") as f:
-                    text = f.read()
-                chunks = splitter.split_text(text)
-                docs = [Document(page_content=chunk, metadata={"title": file}) for chunk in chunks]
-                vector_store.add_documents(docs)
-                print(f"Added {len(docs)} chunks from {file}")
+def load_documents(dir_path: str):
+    for file_path in Path(dir_path).rglob("*.txt"):
+        content = file_path.read_text(encoding="utf-8")
+        chunks = splitter.split_text(content)
+        docs = [Document(page_content=chunk, metadata={"title": file_path.name}) for chunk in chunks]
+        vector_store.add_documents(docs)
+        print(f"Added {len(docs)} chunks from {file_path}")
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Load documents into Qdrant.")
-    parser.add_argument("directory", help="Path to directory with .txt files")
-    args = parser.parse_args()
-    load_directory(args.directory)
\ No newline at end of file
+    if len(sys.argv) != 2:
+        print("Usage: python load_docs.py <directory>")
+        sys.exit(1)
+    load_documents(sys.argv[1])
\ No newline at end of file