Add URL to Brain

files.py

@@ -1,45 +1,75 @@
 import streamlit as st
+from streamlit.runtime.uploaded_file_manager import UploadedFile, UploadedFileRec
 import os
 from loaders.audio import process_audio
 from loaders.txt import process_txt
 from loaders.csv import process_csv
 from loaders.markdown import process_markdown
+from loaders.html import process_html
 from utils import compute_sha1_from_content
 from loaders.pdf import process_pdf
+from loaders.html import get_html, create_html_file, delete_tempfile
+import requests
+import re
+import unicodedata
+import tempfile
 
-def file_uploader(supabase, openai_key, vector_store):
-    file_processors = {
-        ".txt": process_txt,
-        ".csv": process_csv,
-        ".md": process_markdown,
-        ".markdown": process_markdown,
-        ".m4a": process_audio,
-        ".mp3": process_audio,
-        ".webm": process_audio,
-        ".mp4": process_audio,
-        ".mpga": process_audio,
-        ".wav": process_audio,
-        ".mpeg": process_audio,
-        ".pdf": process_pdf,
-    }
+file_processors = {
+    ".txt": process_txt,
+    ".csv": process_csv,
+    ".md": process_markdown,
+    ".markdown": process_markdown,
+    ".m4a": process_audio,
+    ".mp3": process_audio,
+    ".webm": process_audio,
+    ".mp4": process_audio,
+    ".mpga": process_audio,
+    ".wav": process_audio,
+    ".mpeg": process_audio,
+    ".pdf": process_pdf,
+    ".html": process_html,
+}
 
-    files = st.file_uploader("Upload a file", accept_multiple_files=True, type=list(file_processors.keys()))
+def file_uploader(supabase, openai_key, vector_store):
+    files = st.file_uploader("**Upload a file**", accept_multiple_files=True, type=list(file_processors.keys()))
     if st.button("Add to Database"):
         if files is not None:
             for file in files:
-                if file_already_exists(supabase, file):
-                    st.write(f"😎 {file.name} is already in the database.")
-                elif file.size < 1:
-                    st.write(f"💨 {file.name} is empty.")
-                else:
-                    file_extension = os.path.splitext(file.name)[-1]
-                    if file_extension in file_processors:
-                        file_processors[file_extension](vector_store, file)
-                        st.write(f"✅ {file.name} ")
-                    else:
-                        st.write(f"❌ {file.name} is not a valid file type.")
+                filter_file(file, supabase, vector_store)
 
 def file_already_exists(supabase, file):
     file_sha1 = compute_sha1_from_content(file.getvalue())
     response = supabase.table("documents").select("id").eq("metadata->>file_sha1", file_sha1).execute()
-    return len(response.data) > 0
+    return len(response.data) > 0
+
+def filter_file(file, supabase, vector_store):
+    if file_already_exists(supabase, file):
+        st.write(f"😎 {file.name} is already in the database.")
+        return False
+    elif file.size < 1:
+        st.write(f"💨 {file.name} is empty.")
+        return False
+    else:
+        file_extension = os.path.splitext(file.name)[-1]
+        print(file.name, file_extension)
+        if file_extension in file_processors:
+            file_processors[file_extension](vector_store, file)
+            st.write(f"✅ {file.name} ")
+            return True
+        else:
+            st.write(f"❌ {file.name} is not a valid file type.")
+            return False
+
+def url_uploader(supabase, openai_key, vector_store):
+    url = st.text_area("## Add an url",placeholder="https://www.quivr.app")
+    button = st.button("Add the URL to the database")
+    if button:
+        html = get_html(url)
+        if html:
+            st.write(f"Getting content ... {url}  ")
+            file, temp_file_path = create_html_file(url, html)
+            ret = filter_file(file, supabase, vector_store)
+            delete_tempfile(temp_file_path, url, ret)
+        else:
+            st.write(f"❌ Failed to access to {url} .")
+

loaders/html.py

@@ -0,0 +1,47 @@
+from .common import process_file
+from langchain.document_loaders import UnstructuredHTMLLoader
+import requests
+import re
+import unicodedata
+import tempfile
+import os
+import streamlit as st
+from streamlit.runtime.uploaded_file_manager import UploadedFileRec, UploadedFile
+
+def process_html(vector_store, file):
+    return process_file(vector_store, file, UnstructuredHTMLLoader, ".html")
+
+
+def get_html(url):
+    response = requests.get(url)
+    if response.status_code == 200:
+        return response.text
+    else:
+        return None
+
+def create_html_file(url, content):
+    file_name = slugify(url) + ".html"
+    temp_file_path = os.path.join(tempfile.gettempdir(), file_name)
+    with open(temp_file_path, 'w') as temp_file:
+        temp_file.write(content)
+
+    record = UploadedFileRec(id=None, name=file_name, type='text/html', data=open(temp_file_path, 'rb').read())
+    uploaded_file = UploadedFile(record)
+
+    return uploaded_file, temp_file_path
+
+def delete_tempfile(temp_file_path, url, ret):
+    try:
+        os.remove(temp_file_path)
+        if ret:
+            st.write(f"✅ Content saved... {url}  ")
+    except OSError as e:
+        print(f"Error while deleting the temporary file: {str(e)}")
+        if ret:
+            st.write(f"❌ Error while saving content... {url}  ")
+
+def slugify(text):
+    text = unicodedata.normalize('NFKD', text).encode('ascii', 'ignore').decode('utf-8')
+    text = re.sub(r'[^\w\s-]', '', text).strip().lower()
+    text = re.sub(r'[-\s]+', '-', text)
+    return text

main.py

@@ -3,7 +3,7 @@
 import tempfile
 
 import streamlit as st
-from files import file_uploader
+from files import file_uploader, url_uploader
 from question import chat_with_doc
 from brain import brain
 from langchain.embeddings.openai import OpenAIEmbeddings
@@ -63,7 +63,14 @@
         "Select Chunk Size", 100, 1000, st.session_state['chunk_size'], 50)
     st.session_state['chunk_overlap'] = st.sidebar.slider(
         "Select Chunk Overlap", 0, 100, st.session_state['chunk_overlap'], 10)
-    file_uploader(supabase, openai_api_key, vector_store)
+
+    # Create two columns for the file uploader and URL uploader
+    col1, col2 = st.columns(2)
+
+    with col1:
+        file_uploader(supabase, openai_api_key, vector_store)
+    with col2:
+        url_uploader(supabase, openai_api_key, vector_store)
 elif user_choice == 'Chat with your Brain':
     # Display model and temperature selection only when asking questions
     st.sidebar.title("Configuration")