From 4ecc1c06d3ae3f79d1daac556e6743d09787db75 Mon Sep 17 00:00:00 2001
From: mindspawn <sumanthjv@gmail.com>
Date: Fri, 7 Jun 2024 21:18:04 -0700
Subject: [PATCH 1/6] Update main.py

---
 backend/apps/rag/main.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/backend/apps/rag/main.py b/backend/apps/rag/main.py
index d405ef0b4..9df46051a 100644
--- a/backend/apps/rag/main.py
+++ b/backend/apps/rag/main.py
@@ -9,6 +9,7 @@ from fastapi import (
 )
 from fastapi.middleware.cors import CORSMiddleware
 import os, shutil, logging, re
+from datetime import datetime
 
 from pathlib import Path
 from typing import List, Union, Sequence
@@ -30,6 +31,7 @@ from langchain_community.document_loaders import (
     UnstructuredExcelLoader,
     UnstructuredPowerPointLoader,
     YoutubeLoader,
+    OutlookMessageLoader,
 )
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 
@@ -879,6 +881,13 @@ def store_docs_in_vector_db(docs, collection_name, overwrite: bool = False) -> b
     texts = [doc.page_content for doc in docs]
     metadatas = [doc.metadata for doc in docs]
 
+    # ChromaDB does not like datetime formats
+    # for meta-data so convert them to string.
+    for metadata in metadatas:
+        for key, value in metadata.items():
+            if isinstance(value, datetime):
+                metadata[key] = str(value)
+
     try:
         if overwrite:
             for collection in CHROMA_CLIENT.list_collections():
@@ -965,6 +974,7 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
         "swift",
         "vue",
         "svelte",
+        "msg"
     ]
 
     if file_ext == "pdf":
@@ -999,6 +1009,8 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
         "application/vnd.openxmlformats-officedocument.presentationml.presentation",
     ] or file_ext in ["ppt", "pptx"]:
         loader = UnstructuredPowerPointLoader(file_path)
+    elif file_ext == "msg":
+        loader = OutlookMessageLoader(file_path)
     elif file_ext in known_source_ext or (
         file_content_type and file_content_type.find("text/") >= 0
     ):

From f69bc57fed98b4c573836e2a31c354173fc08108 Mon Sep 17 00:00:00 2001
From: mindspawn <sumanthjv@gmail.com>
Date: Fri, 7 Jun 2024 21:18:35 -0700
Subject: [PATCH 2/6] Update requirements.txt

---
 backend/requirements.txt | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/backend/requirements.txt b/backend/requirements.txt
index 7a3668428..57ce2cccf 100644
--- a/backend/requirements.txt
+++ b/backend/requirements.txt
@@ -56,4 +56,6 @@ PyJWT[crypto]==2.8.0
 black==24.4.2
 langfuse==2.33.0
 youtube-transcript-api==0.6.2
-pytube==15.0.0
\ No newline at end of file
+pytube==15.0.0
+
+extract_msg

From cff8534f330b3ed5c81436e438d447fe8e4d4187 Mon Sep 17 00:00:00 2001
From: mindspawn <sumanthjv@gmail.com>
Date: Fri, 7 Jun 2024 21:19:46 -0700
Subject: [PATCH 3/6] Update constants.ts

---
 src/lib/constants.ts | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/lib/constants.ts b/src/lib/constants.ts
index 163309802..5fc1e7b19 100644
--- a/src/lib/constants.ts
+++ b/src/lib/constants.ts
@@ -89,7 +89,8 @@ export const SUPPORTED_FILE_EXTENSIONS = [
 	'xls',
 	'xlsx',
 	'pptx',
-	'ppt'
+	'ppt',
+	'msg'
 ];
 
 // Source: https://kit.svelte.dev/docs/modules#$env-static-public

From d5a2a8a88023d249b2e7e2fbb2f7b8c4e814bd14 Mon Sep 17 00:00:00 2001
From: mindspawn <sumanthjv@gmail.com>
Date: Fri, 7 Jun 2024 21:20:59 -0700
Subject: [PATCH 4/6] Update Dockerfile

---
 Dockerfile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Dockerfile b/Dockerfile
index 2bd05e6ba..498499aa1 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -133,7 +133,8 @@ RUN pip3 install uv && \
     fi; \
     chown -R $UID:$GID /app/backend/data/
 
-
+# Dependency for email message extraction
+RUN pip3 install extract_msg
 
 # copy embedding weight from build
 # RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2

From 6f9148ac4ca12830b00c1cc475b9c7be5bfd4960 Mon Sep 17 00:00:00 2001
From: mindspawn <sumanthjv@gmail.com>
Date: Fri, 7 Jun 2024 21:41:30 -0700
Subject: [PATCH 5/6] Update main.py

---
 backend/apps/rag/main.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/backend/apps/rag/main.py b/backend/apps/rag/main.py
index 9df46051a..8816321b3 100644
--- a/backend/apps/rag/main.py
+++ b/backend/apps/rag/main.py
@@ -974,7 +974,7 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
         "swift",
         "vue",
         "svelte",
-        "msg"
+        "msg",
     ]
 
     if file_ext == "pdf":

From 2412f31ed95fbfa28919ab789b676c7bcfda787a Mon Sep 17 00:00:00 2001
From: mindspawn <sumanthjv@gmail.com>
Date: Fri, 7 Jun 2024 21:47:50 -0700
Subject: [PATCH 6/6] Update Dockerfile to revert duplicated pip install

---
 Dockerfile | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 498499aa1..2bd05e6ba 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -133,8 +133,7 @@ RUN pip3 install uv && \
     fi; \
     chown -R $UID:$GID /app/backend/data/
 
-# Dependency for email message extraction
-RUN pip3 install extract_msg
+
 
 # copy embedding weight from build
 # RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2