langchain_to_chatgpt-retrieval-plugin.py

# STEP 1: Load

# Load documents using LangChain's DocumentLoaders
# This is from https://langchain.readthedocs.io/en/latest/modules/document_loaders/examples/csv.html

from langchain.document_loaders.csv_loader import CSVLoader
loader = CSVLoader(file_path='./example_data/mlb_teams_2012.csv')
data = loader.load()


# STEP 2: Convert

# Convert Document to format expected by https://github.com/openai/chatgpt-retrieval-plugin
from typing import List
from langchain.docstore.document import Document
import json

def write_json(path: str, documents: List[Document])-> None:
    results = [{"text": doc.page_content} for doc in documents]
    with open(path, "w") as f:
        json.dump(results, f, indent=2)

write_json("foo.json", data)

# STEP 3: Use

# Ingest this as you would any other json file in https://github.com/openai/chatgpt-retrieval-plugin/tree/main/scripts/process_json