From 30620c0201bfbb1737c64b1106501cd44078af78 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=A0=D0=B8=D0=BD=D0=B0=D1=80=20=D0=9C=D0=B8=D1=80=D0=B7?=
 =?UTF-8?q?=D0=B0=D0=B3=D0=B8=D1=82=D0=BE=D0=B2?= <mirzagitov03@mail.ru>
Date: Thu, 11 Jun 2026 09:16:31 +0000
Subject: [PATCH] =?UTF-8?q?=D0=A0=D0=B5=D1=88=D0=B5=D0=BD=D0=B8=D0=B5=20?=
 =?UTF-8?q?=D0=B3=D0=BE=D1=82=D0=BE=D0=B2=D0=BE=20=D0=BA=20=D0=BF=D1=83?=
 =?UTF-8?q?=D0=B1=D0=BB=D0=B8=D0=BA=D0=B0=D1=86=D0=B8=D0=B8:=20add=20vecto?=
 =?UTF-8?q?rstore.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 vectorstore.py | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)
 create mode 100644 vectorstore.py

diff --git a/vectorstore.py b/vectorstore.py
new file mode 100644
index 0000000..d0192e9
--- /dev/null
+++ b/vectorstore.py
@@ -0,0 +1,46 @@
+"""
+RAG vector store using ChromaDB and Ollama embeddings.
+"""
+
+from pathlib import Path
+from typing import List, Iterable
+
+import chromadb
+from langchain.embeddings.ollama import OllamaEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.schema.document import Document
+
+CHROMA_DIR = "./chroma_db"
+EMBED_MODEL = "nomic-embed-text"
+
+
+def create_vectorstore(persist_directory: str = CHROMA_DIR):
+    """Create or load a Chroma vector store.
+
+    Parameters
+    ----------
+    persist_directory:
+        Directory where the Chroma database is stored. If it does not exist, it will be created.
+    """
+    embeddings = OllamaEmbeddings(model=EMBED_MODEL)
+    client = chromadb.PersistentClient(path=persist_directory)
+    # Use a single collection named "documents"
+    return client.get_or_create_collection(name="documents", embedding_function=embeddings)
+
+
+def load_documents(directory: str, vectorstore) -> None:
+    """Load all .txt and .md files from *directory*, chunk them and add to the vector store.
+
+    The function does not return anything; it mutates the provided collection.
+    """
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    docs: List[Document] = []
+    for path in Path(directory).rglob("*.txt"):
+        content = path.read_text(encoding="utf-8")
+        docs.extend(text_splitter.create_documents([content], metadata={"source": str(path)}))
+    for path in Path(directory).rglob("*.md"):
+        content = path.read_text(encoding="utf-8")
+        docs.extend(text_splitter.create_documents([content], metadata={"source": str(path)}))
+
+    if docs:
+        vectorstore.add(documents=docs)