parse_py / save_to_hf.py
broadfield-dev's picture
Create save_to_hf.py
90e461b verified
raw
history blame
847 Bytes
# save_to_hf.py
from datasets import Dataset
import chromadb
from database import init_chromadb, create_collection
def save_chromadb_to_hf(dataset_name="python_program_vectors"):
client = init_chromadb()
collection = create_collection(client)
# Fetch all data from ChromaDB
results = collection.get(include=["documents", "metadatas", "embeddings"])
data = {
"code": results["documents"],
"sequence": [meta["sequence"] for meta in results["metadatas"]],
"vectors": results["embeddings"]
}
# Create a Hugging Face Dataset
dataset = Dataset.from_dict(data)
# Push to Hugging Face Hub
dataset.push_to_hub(dataset_name, token="YOUR_HUGGINGFACE_TOKEN")
print(f"Dataset pushed to Hugging Face Hub as {dataset_name}")
if __name__ == "__main__":
save_chromadb_to_hf()