Harrison/whatsapp loader (#2085)

Co-authored-by: Moshe <hello@moshemalka.me>

docs/modules/indexes/document_loaders/examples/example_data/whatsapp_chat.txt

@@ -0,0 +1,11 @@
+1/22/23, 6:30 PM - User 1: Hi! Im interested in your bag. Im offering $50. Let me know if you are interested. Thanks!
+1/22/23, 8:24 PM - User 2: Goodmorning! $50 is too low.
+1/23/23, 2:59 AM - User 1: How much do you want?
+1/23/23, 3:00 AM - User 2: Online is at least $100
+1/23/23, 3:01 AM - User 2: Here is $129
+1/23/23, 3:01 AM - User 2: <Media omitted>
+1/23/23, 3:01 AM - User 1: Im not interested in this bag. Im interested in the blue one!
+1/23/23, 3:02 AM - User 1: I thought you were selling the blue one!
+1/23/23, 3:18 AM - User 2: No Im sorry it was my mistake, the blue one is not for sale
+1/23/23, 3:19 AM - User 1: Oh no worries! Bye
+1/23/23, 3:19 AM - User 2: Bye!

docs/modules/indexes/document_loaders/examples/whatsapp_chat.ipynb

@@ -0,0 +1,67 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### WhatsApp Chat\n",
+    "\n",
+    "This notebook covers how to load data from the WhatsApp Chats into a format that can be ingested into LangChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import WhatsAppChatLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = WhatsAppChatLoader(\"example_data/whatsapp_chat.txt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader.load()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.1"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "384707f4965e853a82006e90614c2e1a578ea1f6eb0ee07a1dd78a657d37dd67"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

langchain/document_loaders/__init__.py

@@ -55,6 +55,7 @@ from langchain.document_loaders.unstructured import (
 )
 from langchain.document_loaders.url import UnstructuredURLLoader
 from langchain.document_loaders.web_base import WebBaseLoader
+from langchain.document_loaders.whatsapp_chat import WhatsAppChatLoader
 from langchain.document_loaders.word_document import UnstructuredWordDocumentLoader
 from langchain.document_loaders.youtube import (
     GoogleApiClient,
@@ -113,6 +114,7 @@ __all__ = [
     "GoogleApiClient",
     "CSVLoader",
     "BlackboardLoader",
+    "WhatsAppChatLoader",
     "DataFrameLoader",
     "AzureBlobStorageFileLoader",
     "AzureBlobStorageContainerLoader",

langchain/document_loaders/whatsapp_chat.py

@@ -0,0 +1,40 @@
+import re
+from pathlib import Path
+from typing import List
+
+from langchain.docstore.document import Document
+from langchain.document_loaders.base import BaseLoader
+
+
+def concatenate_rows(date: str, sender: str, text: str) -> str:
+    """Combine message information in a readable format ready to be used."""
+    return f"{sender} on {date}: {text}\n\n"
+
+
+class WhatsAppChatLoader(BaseLoader):
+    """Loader that loads WhatsApp messages text file."""
+
+    def __init__(self, path: str):
+        """Initialize with path."""
+        self.file_path = path
+
+    def load(self) -> List[Document]:
+        """Load documents."""
+        p = Path(self.file_path)
+        text_content = ""
+
+        with open(p, encoding="utf8") as f:
+            lines = f.readlines()
+
+        for line in lines:
+            result = re.match(
+                r"(\d{1,2}/\d{1,2}/\d{2,4}, \d{1,2}:\d{1,2} (?:AM|PM)) - (.*?): (.*)",
+                line.strip(),
+            )
+            if result:
+                date, sender, text = result.groups()
+                text_content += concatenate_rows(date, sender, text)
+
+        metadata = {"source": str(p)}
+
+        return [Document(page_content=text_content, metadata=metadata)]