initialize.py

from langchain_google_genai import GoogleGenerativeAIEmbeddings
from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import Chroma
import os
import gen_splits
from langchain_ollama import OllamaEmbeddings
import ollama
import chromadb


GEMINI_API_KEY = os.environ.get('GEMINI_API_KEY')
OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY')

# Using Google GenAI Text Embeddings  
# embedding_model = GoogleGenerativeAIEmbeddings(model="models/embedding-001", task_type="retrieval_query", google_api_key=GEMINI_API_KEY)         ###

embedding_model = OpenAIEmbeddings(api_key=OPENAI_API_KEY, model="text-embedding-3-small")

#embedding_model = OllamaEmbeddings(model="mxbai-embed-large")

# Create Embeddings for Searching the Splits
persist_directory = './chroma/'

def initialize():
    splits = gen_splits.gen_splits()
    vectordb = Chroma.from_documents(documents=splits, persist_directory=persist_directory, embedding=embedding_model)
    vectordb.persist()
    return vectordb



if __name__ == "__main__":
    vectordb = initialize()