Add cost estimate feature

Calculates number of tokens/user cost and requires user permission to proceed.

User permission bypass is built-in to allow for non-human users.

scripts/ingest_rst.py

@@ -5,14 +5,48 @@ from langchain.vectorstores import FAISS
 from langchain.embeddings import OpenAIEmbeddings
 import pickle
 import dotenv
+import tiktoken
+import sys
 
-dotenv.load_dotenv()
+def num_tokens_from_string(string: str, encoding_name: str) -> int:
+# Function to convert string to tokens and estimate user cost.
+    encoding = tiktoken.get_encoding(encoding_name)
+    num_tokens = len(encoding.encode(string))
+    total_price = ((num_tokens/1000) * 0.0004)
+    return num_tokens, total_price
+
+def call_openai_api():
+# Function to create a vector store from the documents and save it to disk.
+    store = FAISS.from_texts(docs, OpenAIEmbeddings(), metadatas=metadatas)
+    faiss.write_index(store.index, "docs.index")
+    store.index = None
+    with open("faiss_store.pkl", "wb") as f:
+        pickle.dump(store, f)
 
+def get_user_permission():
+# Function to ask user permission to call the OpenAI api and spend their OpenAI funds.
+    # Here we convert the docs list to a string and calculate the number of OpenAI tokens the string represents.
+    docs_content = (" ".join(docs))
+    tokens, total_price = num_tokens_from_string(string=docs_content, encoding_name="cl100k_base")
+    # Here we print the number of tokens and the approx user cost with some visually appealing formatting. 
+    print(f"Number of Tokens = {format(tokens, ',d')}")
+    print(f"Approx Cost = ${format(total_price, ',.2f')}")
+    #Here we check for user permission before calling the API.
+    user_input = input("Price Okay? (Y/N) \n").lower()
+    if user_input == "y":
+        call_openai_api()
+    elif user_input == "":
+        call_openai_api()
+    else:
+        print("The API was not called. No money was spent.")
+
+#Load .env file
+dotenv.load_dotenv()
 
 # Here we load in the data in the format that Notion exports it in.
 ps = list(Path("scikit-learn").glob("**/*.rst"))
-# parse all child directories
 
+# parse all child directories
 data = []
 sources = []
 for p in ps:
@@ -30,10 +64,14 @@ for i, d in enumerate(data):
     docs.extend(splits)
     metadatas.extend([{"source": sources[i]}] * len(splits))
 
-
+# Here we check for command line arguments for bot calls. 
-# Here we create a vector store from the documents and save it to disk.
+# If no argument exists or the permission_bypass_flag argument is not '-y', 
-store = FAISS.from_texts(docs, OpenAIEmbeddings(), metadatas=metadatas)
+# user permission is requested to call the API. 
-faiss.write_index(store.index, "docs.index")
+if len(sys.argv) > 1:
-store.index = None
+    permission_bypass_flag = sys.argv[1]
-with open("faiss_store.pkl", "wb") as f:
+    if permission_bypass_flag == '-y':
-    pickle.dump(store, f)
+        call_openai_api()
+    else:
+        get_user_permission()  
+else:
+    get_user_permission()

scripts/ingest_rst_sphinx.py

@@ -1,6 +1,8 @@
 import os
 import pickle
 import dotenv
+import tiktoken
+import sys
 import faiss
 import shutil
 from pathlib import Path
@@ -28,6 +30,38 @@ def convert_rst_to_txt(src_dir, dst_dir):
                f"-C {dst_dir} "
         sphinx_main(args.split())
 
+def num_tokens_from_string(string: str, encoding_name: str) -> int:
+# Function to convert string to tokens and estimate user cost.
+    encoding = tiktoken.get_encoding(encoding_name)
+    num_tokens = len(encoding.encode(string))
+    total_price = ((num_tokens/1000) * 0.0004)
+    return num_tokens, total_price
+
+def call_openai_api():
+# Function to create a vector store from the documents and save it to disk.
+    store = FAISS.from_texts(docs, OpenAIEmbeddings(), metadatas=metadatas)
+    faiss.write_index(store.index, "docs.index")
+    store.index = None
+    with open("faiss_store.pkl", "wb") as f:
+        pickle.dump(store, f)
+
+def get_user_permission():
+# Function to ask user permission to call the OpenAI api and spend their OpenAI funds.
+    # Here we convert the docs list to a string and calculate the number of OpenAI tokens the string represents.
+    docs_content = (" ".join(docs))
+    tokens, total_price = num_tokens_from_string(string=docs_content, encoding_name="cl100k_base")
+    # Here we print the number of tokens and the approx user cost with some visually appealing formatting. 
+    print(f"Number of Tokens = {format(tokens, ',d')}")
+    print(f"Approx Cost = ${format(total_price, ',.2f')}")
+    #Here we check for user permission before calling the API.
+    user_input = input("Price Okay? (Y/N) \n").lower()
+    if user_input == "y":
+        call_openai_api()
+    elif user_input == "":
+        call_openai_api()
+    else:
+        print("The API was not called. No money was spent.")
+
 #Load .env file
 dotenv.load_dotenv()
 
@@ -58,13 +92,17 @@ for i, d in enumerate(data):
     docs.extend(splits)
     metadatas.extend([{"source": sources[i]}] * len(splits))
 
-
+# Here we check for command line arguments for bot calls. 
-# Here we create a vector store from the documents and save it to disk.
+# If no argument exists or the permission_bypass_flag argument is not '-y', 
-store = FAISS.from_texts(docs, OpenAIEmbeddings(), metadatas=metadatas)
+# user permission is requested to call the API.  
-faiss.write_index(store.index, "docs.index")
+if len(sys.argv) > 1:
-store.index = None
+    permission_bypass_flag = sys.argv[1]
-with open("faiss_store.pkl", "wb") as f:
+    if permission_bypass_flag == '-y':
-    pickle.dump(store, f)
+        call_openai_api()
+    else:
+        get_user_permission()  
+else:
+    get_user_permission()
 
 # Delete tmp folder
 # Commented out for now