Merge pull request #547 from Marclass/main

feat: Add reStructuredText specific parser for RAG

backend/apps/rag/main.py

@@ -22,6 +22,7 @@ from langchain_community.document_loaders import (
     UnstructuredWordDocumentLoader,
     UnstructuredMarkdownLoader,
     UnstructuredXMLLoader,
+    UnstructuredRSTLoader,
 )
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import Chroma
@@ -178,6 +179,8 @@ def store_doc(
             loader = Docx2txtLoader(file_path)
         elif file_ext=="csv":
             loader = CSVLoader(file_path)
+        elif file_ext=="rst":
+            loader = UnstructuredRSTLoader(file_path, mode="elements")
         elif file_ext in text_xml:
             loader=UnstructuredXMLLoader(file_path)
         elif file_ext in known_source_ext or file.content_type.find("text/")>=0:

src/lib/components/chat/MessageInput.svelte

@@ -8,7 +8,7 @@
 	import Suggestions from './MessageInput/Suggestions.svelte';
 	import { uploadDocToVectorDB } from '$lib/apis/rag';
 	import AddFilesPlaceholder from '../AddFilesPlaceholder.svelte';
-	import { SUPPORTED_FILE_TYPE } from '$lib/constants';
+	import { SUPPORTED_FILE_TYPE, SUPPORTED_FILE_EXTENSIONS } from '$lib/constants';
 	import Documents from './MessageInput/Documents.svelte';
 	import Models from './MessageInput/Models.svelte';
 
@@ -169,11 +169,13 @@
 						reader.readAsDataURL(file);
 					} else if (
 						SUPPORTED_FILE_TYPE.includes(file['type']) ||
-						['md'].includes(file.name.split('.').at(-1))
+						SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
 					) {
 						uploadDoc(file);
 					} else {
-						toast.error(`Unknown File Type '${file['type']}', but accepting and treating as plain text`);
+						toast.error(
+							`Unknown File Type '${file['type']}', but accepting and treating as plain text`
+						);
 						uploadDoc(file);
 					}
 				} else {
@@ -304,12 +306,14 @@
 								reader.readAsDataURL(file);
 							} else if (
 								SUPPORTED_FILE_TYPE.includes(file['type']) ||
-								['md'].includes(file.name.split('.').at(-1))
+								SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
 							) {
 								uploadDoc(file);
 								filesInputElement.value = '';
 							} else {
-								toast.error(`Unknown File Type '${file['type']}', but accepting and treating as plain text`);
+								toast.error(
+									`Unknown File Type '${file['type']}', but accepting and treating as plain text`
+								);
 								uploadDoc(file);
 								filesInputElement.value = '';
 							}
@@ -466,8 +470,8 @@
 							placeholder={chatInputPlaceholder !== ''
 								? chatInputPlaceholder
 								: speechRecognitionListening
-									? 'Listening...'
-									: 'Send a message'}
+								? 'Listening...'
+								: 'Send a message'}
 							bind:value={prompt}
 							on:keypress={(e) => {
 								if (e.keyCode == 13 && !e.shiftKey) {

src/lib/constants.ts

@@ -21,9 +21,11 @@ export const SUPPORTED_FILE_TYPE = [
 	'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
 	'application/octet-stream',
 	'application/x-javascript',
-	'text/markdown',
+	'text/markdown'
 ];
 
+export const SUPPORTED_FILE_EXTENSIONS = ['md', 'rst'];
+
 // Source: https://kit.svelte.dev/docs/modules#$env-static-public
 // This feature, akin to $env/static/private, exclusively incorporates environment variables
 // that are prefixed with config.kit.env.publicPrefix (usually set to PUBLIC_).

src/routes/(app)/documents/+page.svelte

@@ -7,7 +7,7 @@
 	import { documents } from '$lib/stores';
 	import { createNewDoc, deleteDocByName, getDocs } from '$lib/apis/documents';
 
-	import { SUPPORTED_FILE_TYPE } from '$lib/constants';
+	import { SUPPORTED_FILE_TYPE, SUPPORTED_FILE_EXTENSIONS } from '$lib/constants';
 	import { uploadDocToVectorDB } from '$lib/apis/rag';
 	import { transformFileName } from '$lib/utils';
 
@@ -69,11 +69,13 @@
 				const file = inputFiles[0];
 				if (
 					SUPPORTED_FILE_TYPE.includes(file['type']) ||
-					['md'].includes(file.name.split('.').at(-1))
+					SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
 				) {
 					uploadDoc(file);
 				} else {
-					toast.error(`Unknown File Type '${file['type']}', but accepting and treating as plain text`);
+					toast.error(
+						`Unknown File Type '${file['type']}', but accepting and treating as plain text`
+					);
 					uploadDoc(file);
 				}
 			} else {
@@ -150,11 +152,13 @@
 						const file = inputFiles[0];
 						if (
 							SUPPORTED_FILE_TYPE.includes(file['type']) ||
-							['md'].includes(file.name.split('.').at(-1))
+							SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
 						) {
 							uploadDoc(file);
 						} else {
-							toast.error(`Unknown File Type '${file['type']}', but accepting and treating as plain text`);
+							toast.error(
+								`Unknown File Type '${file['type']}', but accepting and treating as plain text`
+							);
 							uploadDoc(file);
 						}