Merge pull request #87 from arc53/ingest-cli

Ingest cli

application/requirements.txt

@@ -60,6 +60,7 @@ tiktoken==0.1.2
 tokenizers==0.13.2
 tqdm==4.64.1
 transformers==4.26.0
+typer==0.7.0
 typing-inspect==0.8.0
 typing_extensions==4.4.0
 urllib3==1.26.14

scripts/ingest.py

@@ -1,6 +1,9 @@
 import sys
 import nltk
 import dotenv
+import typer
+
+from typing import List, Optional
 
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 
@@ -10,28 +13,52 @@ from parser.open_ai_func import call_openai_api, get_user_permission
 
 dotenv.load_dotenv()
 
-#Specify your folder HERE
-directory_to_ingest = 'inputs'
+app = typer.Typer(add_completion=False)
 
-nltk.download('punkt')
-nltk.download('averaged_perceptron_tagger')
+nltk.download('punkt', quiet=True)
+nltk.download('averaged_perceptron_tagger', quiet=True)
 
 #Splits all files in specified folder to documents
-raw_docs = SimpleDirectoryReader(input_dir=directory_to_ingest).load_data()
-raw_docs = [Document.to_langchain_format(raw_doc) for raw_doc in raw_docs]
-# Here we split the documents, as needed, into smaller chunks.
-# We do this due to the context limits of the LLMs.
-text_splitter = RecursiveCharacterTextSplitter()
-docs = text_splitter.split_documents(raw_docs)
+@app.command()
+def ingest(directory: Optional[str] = typer.Option("inputs",
+                                                   help="Path to the directory for index creation."),
+           files: Optional[List[str]] = typer.Option(None,
+                                                   help="""File paths to use (Optional; overrides directory).
+                                                        E.g. --files inputs/1.md --files inputs/2.md"""),
+           recursive: Optional[bool] = typer.Option(True,
+                                                   help="Whether to recursively search in subdirectories."),
+           limit: Optional[int] = typer.Option(None,
+                                                   help="Maximum number of files to read."),
+           formats: Optional[List[str]] = typer.Option([".rst", ".md"],
+                                                   help="""List of required extensions (list with .)
+                                                        Currently supported: .rst, .md, .pdf, .docx, .csv, .epub"""),
+           exclude: Optional[bool] = typer.Option(True, help="Whether to exclude hidden files (dotfiles).")):
 
-# Here we check for command line arguments for bot calls.
-# If no argument exists or the permission_bypass_flag argument is not '-y',
-# user permission is requested to call the API.
-if len(sys.argv) > 1:
-    permission_bypass_flag = sys.argv[1]
-    if permission_bypass_flag == '-y':
-        call_openai_api(docs)
+    """
+        Creates index from specified location or files.
+        By default /inputs folder is used, .rst and .md are parsed.
+    """
+    raw_docs = SimpleDirectoryReader(input_dir=directory, input_files=files, recursive=recursive,
+                                     required_exts=formats, num_files_limit=limit,
+                                     exclude_hidden=exclude).load_data()
+    raw_docs = [Document.to_langchain_format(raw_doc) for raw_doc in raw_docs]
+    print(raw_docs)
+    # Here we split the documents, as needed, into smaller chunks.
+    # We do this due to the context limits of the LLMs.
+    text_splitter = RecursiveCharacterTextSplitter()
+    docs = text_splitter.split_documents(raw_docs)
+
+    # Here we check for command line arguments for bot calls.
+    # If no argument exists or the permission_bypass_flag argument is not '-y',
+    # user permission is requested to call the API.
+    if len(sys.argv) > 1:
+        permission_bypass_flag = sys.argv[1]
+        if permission_bypass_flag == '-y':
+            call_openai_api(docs)
+        else:
+            get_user_permission(docs)
     else:
         get_user_permission(docs)
-else:
-    get_user_permission(docs)
+
+if __name__ == "__main__":
+  app()