From 0881f0600d7e760cd0a19dcddb67d5ce8ee5aee6 Mon Sep 17 00:00:00 2001
From: anovazzi1 <otavio2204@gmail.com>
Date: Mon, 15 Jan 2024 19:57:39 -0300
Subject: [PATCH] Refactor document loaders to support metadata

---
 .../CollegeConfidentialLoader.py               | 12 +++++++++---
 .../documentloaders/FacebookChatLoader.py      | 18 ++++++++++--------
 2 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/src/backend/langflow/components/documentloaders/CollegeConfidentialLoader.py b/src/backend/langflow/components/documentloaders/CollegeConfidentialLoader.py
index 654932fd5..44fc8c9ab 100644
--- a/src/backend/langflow/components/documentloaders/CollegeConfidentialLoader.py
+++ b/src/backend/langflow/components/documentloaders/CollegeConfidentialLoader.py
@@ -2,6 +2,7 @@
 from langflow import CustomComponent
 from langchain.docstore.document import Document
 from typing import Optional
+from langchain_community.document_loaders.college_confidential import CollegeConfidentialLoader
 
 class CollegeConfidentialLoaderComponent(CustomComponent):
     display_name = "CollegeConfidentialLoader"
@@ -19,6 +20,11 @@ class CollegeConfidentialLoaderComponent(CustomComponent):
         web_path: str,
         metadata: Optional[dict] = {}
     ) -> Document:
-        # Assuming there is a loader class `CollegeConfidentialLoader` that takes `metadata` and `web_path` as arguments
-        # Replace `CollegeConfidentialLoader` with the actual class name if different
-        return CollegeConfidentialLoader(web_path=web_path, metadata=metadata)
+        documents = CollegeConfidentialLoader(web_path=web_path).load()
+        if(metadata):
+            for document in documents:
+                if not document.metadata:
+                    document.metadata = metadata
+                else:
+                    document.metadata.update(metadata)
+        return documents
diff --git a/src/backend/langflow/components/documentloaders/FacebookChatLoader.py b/src/backend/langflow/components/documentloaders/FacebookChatLoader.py
index d5b3c1dd1..deb636eac 100644
--- a/src/backend/langflow/components/documentloaders/FacebookChatLoader.py
+++ b/src/backend/langflow/components/documentloaders/FacebookChatLoader.py
@@ -2,7 +2,7 @@
 from langflow import CustomComponent
 from langchain.docstore.document import Document
 from typing import Optional, Dict
-
+from langchain_community.document_loaders.facebook_chat import FacebookChatLoader
 class FacebookChatLoaderComponent(CustomComponent):
     display_name = "FacebookChatLoader"
     description = "Load `Facebook Chat` messages directory dump."
@@ -13,8 +13,7 @@ class FacebookChatLoaderComponent(CustomComponent):
             "file_path": {
                 "display_name": "File Path",
                 "required": True,
-                "suffixes": [".json"],
-                "file_types": ["json"],
+                "file_types": [".json"],
                 "field_type": "file",
             },
             "metadata": {
@@ -25,8 +24,11 @@ class FacebookChatLoaderComponent(CustomComponent):
         }
 
     def build(self, file_path: str, metadata: Optional[Dict] = None) -> Document:
-        # Assuming there is a class named FacebookChatLoader that takes file_path and metadata as parameters
-        # and returns a Document object. Replace 'FacebookChatLoader' with the actual class name.
-        # As per the JSON, the output type is 'Document', which is part of langchain.documents.
-        # Therefore, the 'FacebookChatLoader' should be imported or defined elsewhere in the codebase.
-        return FacebookChatLoader(file_path=file_path, metadata=metadata)
\ No newline at end of file
+        documents = FacebookChatLoader(file_path=file_path).load()
+        if(metadata):
+            for document in documents:
+                if not document.metadata:
+                    document.metadata = metadata
+                else:
+                    document.metadata.update(metadata)
+        return documents
\ No newline at end of file