Embedding

# Filename: embeddings.py
# pip install langchain sentence_transformers

import sys
import json
from langchain_huggingface.embeddings import HuggingFaceEmbeddings

if __name__ == "__main__":
    embeddings = HuggingFaceEmbeddings(
        model_name="sentence-transformers/all-MiniLM-L6-v2"
    )
    
    # Get the JSON file's path.
    if len(sys.argv) < 2:
        print("Error: Specify the path to the input JSON file.")
        print("For example, 'python embeddings.py myfile.json'")
        sys.exit(1)

    file_path = sys.argv[1]
    
    try:
        # Get the JSON file's contents.
        with open(file_path, 'r') as file:
            file_elements = json.load(file)

        # Process each element in the JSON file.
        for element in file_elements:
            # Get the element's "text" field.
            text = element["text"]
            # Generate the embeddings for that "text" field.
            query_result = embeddings.embed_query(text)
            # Add the embeddings to that element as an "embeddings" field.
            element["embeddings"] = query_result

        # Save the updated JSON back into the original file.
        with open(file_path, 'w') as file:
            json.dump(file_elements, file, indent=2)

        print(f"Done! Updated JSON saved to '{file_path}'.")

    except FileNotFoundError:
        print(f"Error: File '{file_path}' not found.")
    except IOError:
        print(f"Error: Unable to access file '{file_path}'.")