Adding URL summary option to DocSum Gradio-UI (#1248)

Signed-off-by: okhleif-IL <omar.khleif@intel.com>
Co-authored-by: okhleif-IL <omar.khleif@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: lkk <33276950+lkk12014402@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
Co-authored-by: WenjiaoYue <wenjiao.yue@intel.com>

DocSum/ui/gradio/docsum_ui_gradio.py

@@ -6,12 +6,13 @@ import base64
 import json
 import logging
 import os
+from urllib.parse import urlparse
 
 import gradio as gr
 import requests
 import uvicorn
 from fastapi import FastAPI
-from langchain_community.document_loaders import Docx2txtLoader, PyPDFLoader
+from langchain_community.document_loaders import Docx2txtLoader, PyPDFLoader, UnstructuredURLLoader
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -91,6 +92,42 @@ class DocSumUI:
         base64_str = self.encode_file_to_base64(file)
         return self.generate_summary(base64_str, document_type="video")
 
+    def is_valid_url(self, url):
+        try:
+            result = urlparse(url)
+            return all([result.scheme, result.netloc])
+        except ValueError:
+            return False
+
+    def read_url(self, url):
+        """Read and process the content of a url.
+
+        Args:
+            url: The url to be read as a document.
+
+        Returns:
+            str: The content of the website or an error message if the url is unsupported.
+        """
+
+        self.page_content = ""
+
+        logger.info(">>> Reading url: %s", url)
+        if self.is_valid_url(url=url):
+            os.environ["no_proxy"] = f"{os.environ.get('no_proxy', '')},{url}".strip(",")
+            try:
+                loader = UnstructuredURLLoader([url])
+                page = loader.load()
+                self.page_content = [content.page_content for content in page][0]
+            except Exception as e:
+                msg = f"There was an error trying to read '{url}' --> '{e}'\nTry adding the domain name to your `no_proxy` variable and try again. Example: example.com*"
+                logger.error(msg)
+        else:
+            msg = f"Invalid URL '{url}'. Make sure the link provided is a valid URL"
+            logger.error(msg)
+            return msg
+
+        return self.page_content
+
     def generate_summary(self, doc_content, document_type="text"):
         """Generate a summary for the given document content.
 
@@ -201,6 +238,25 @@ class DocSumUI:
                     )
             submit_btn.click(fn=self.generate_summary, inputs=[input_text], outputs=[generated_text])
 
+        with gr.Blocks() as url_ui:
+            # URL text UI
+            with gr.Row():
+                with gr.Column():
+                    input_text = gr.TextArea(
+                        label="Please paste a URL for summarization",
+                        placeholder="Paste a URL for the information you need to summarize",
+                    )
+                    submit_btn = gr.Button("Generate Summary")
+                with gr.Column():
+                    generated_text = gr.TextArea(
+                        label="Text Summary", placeholder="Summarized text will be displayed here"
+                    )
+            submit_btn.click(
+                lambda input_text: self.generate_summary(self.read_url(input_text)),
+                inputs=input_text,
+                outputs=generated_text,
+            )
+
         # File Upload UI
         file_ui = self.create_upload_ui(
             label="Please upload a document (.pdf, .doc, .docx)",
@@ -232,6 +288,8 @@ class DocSumUI:
                     audio_ui.render()
                 with gr.TabItem("Upload Video"):
                     video_ui.render()
+                with gr.TabItem("Enter URL"):
+                    url_ui.render()
 
         return self.demo
 

DocSum/ui/gradio/requirements.txt

@@ -6,3 +6,4 @@ numpy==1.26.4
 opencv-python==4.10.0.82
 Pillow==10.3.0
 pypdf
+unstructured