WIP - Streamlit UI, firecrawl - V0.5

lib/ai_writers/keywords_to_blog_streamlit.py

@@ -74,11 +74,11 @@ def write_blog_from_keywords(search_keywords, url=None):
             if blog_markdown_str and tavily_search_result:
                 logger.info(f"\n\n######### Blog content after Tavily AI research: ######### \n\n")
                 blog_markdown_str = write_blog_google_serp(search_keywords, tavily_search_result)
-                status.update(label="Finished Writing Blog From Tavily Results:{blog_markdown_str}")
+                status.update(label="Finished Writing Blog From Tavily Results:{blog_markdown_str}", expanded=True)
         except Exception as err:
             logger.error(f"Failed to do Tavily AI research: {err}")
 
-        status.update(label="🙎 Generating - Title, Meta Description, Tags, Categories for the content.")
+        status.update(label="🙎 Generating - Title, Meta Description, Tags, Categories for the content.", expanded=True)
         try:
             blog_title, blog_meta_desc, blog_tags, blog_categories = blog_metadata(blog_markdown_str)
         except Exception as err:
@@ -87,21 +87,14 @@ def write_blog_from_keywords(search_keywords, url=None):
         try:
             generated_image_filepath = generate_image(f"{blog_title} + ' ' + {blog_meta_desc}")
         except Exception as err:
-            st.error(f"Failed in Image generation: {err}")
+            st.warning(f"Failed in Image generation: {err}")
 
         saved_blog_to_file = save_blog_to_file(blog_markdown_str, blog_title, blog_meta_desc, 
                             blog_tags, blog_categories, generated_image_filepath)
         status.update(label=f"Saved the content in this file: {saved_blog_to_file}")
-        blog_frontmatter = dedent(f"""
-        \n---------------------------------------------------------------------
-        title: {blog_title.strip()}\n
-        categories: [{blog_categories.strip()}]\n
-        tags: [{blog_tags.strip()}]\n
-        Meta description: {blog_meta_desc.replace(":", "-").strip()}\n
-        ---------------------------------------------------------------------\n
-        """)
         logger.info(f"\n\n --------- Finished writing Blog for : {search_keywords} -------------- \n")
-        st.markdown(f"{blog_frontmatter}")
+       
+        # Render the result on streamlit UI
         st.image(generated_image_filepath)
         st.markdown(f"{blog_markdown_str}")
-        status.update(label=f"Finished, Review & Use your Original Content Below: {saved_blog_to_file}")
+        status.update(label=f"Finished, Review & Use your Original Content Below: {saved_blog_to_file}", state="complete")

lib/blog_metadata/get_blog_metadata.py

@@ -1,28 +1,52 @@
 import sys
 import streamlit as st
-
 from loguru import logger
+import random
+import time
+
 logger.remove()
 logger.add(sys.stdout,
-        colorize=True,
-        format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
-    )   
+           colorize=True,
+           format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
+           )
 
 from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
 
-
 def blog_metadata(blog_article):
     """ Common function to get blog metadata """
     logger.info(f"Generating Content MetaData\n")
+    
+    progress_bar = st.progress(0)
+    total_steps = 4
 
+    # Step 1: Generate blog title
+    time.sleep(random.uniform(1, 3))
     blog_title = generate_blog_title(blog_article)
+    progress_bar.progress(1 / total_steps)
+
+    # Step 2: Generate blog meta description
+    time.sleep(random.uniform(1, 3))
     blog_meta_desc = generate_blog_description(blog_article)
+    progress_bar.progress(2 / total_steps)
+
+    # Step 3: Generate blog tags
+    time.sleep(random.uniform(1, 3))
     blog_tags = get_blog_tags(blog_article)
+    progress_bar.progress(3 / total_steps)
+
+    # Step 4: Generate blog categories
+    time.sleep(random.uniform(1, 3))
     blog_categories = get_blog_categories(blog_article)
+    progress_bar.progress(4 / total_steps)
+
+    # Present the result in a table format
+    st.table({
+        "Metadata": ["Blog Title", "Meta Description", "Tags", "Categories"],
+        "Value": [blog_title, blog_meta_desc, blog_tags, blog_categories]
+    })
 
     return blog_title, blog_meta_desc, blog_tags, blog_categories
 
-
 def generate_blog_title(blog_article):
     """
     Given a blog title generate an outline for it
@@ -43,7 +67,6 @@ def generate_blog_title(blog_article):
         logger.error(f"Failed to get response from LLM: {err}")
         raise err
 
-
 def generate_blog_description(blog_content):
     """
         Prompt designed to give SEO optimized blog descripton
@@ -62,7 +85,6 @@ def generate_blog_description(blog_content):
         logger.error(f"Failed to get response from LLM:{err}")
         raise err
 
-
 def get_blog_categories(blog_article):
     """
     Function to generate blog categories for given blog content.
@@ -80,12 +102,10 @@ def get_blog_categories(blog_article):
     except Exception as err:
         logger.error(f"get_blog_categories:Failed to get response from LLM: {err}")
 
-
 def get_blog_tags(blog_article):
     """
         Function to suggest tags for the given blog content
     """
-    # Suggest at least 5 tags for the following blog post [Enter your blog post text here].
     prompt = f"""As an expert SEO and blog writer, suggest only 2 relevant and specific blog tags
          for the given blog content. Only reply with comma separated values.
          Blog content:  {blog_article}."""
@@ -96,3 +116,4 @@ def get_blog_tags(blog_article):
     except Exception as err:
         logger.error(f"Failed to get response from LLM: {err}")
         raise err
+

lib/gpt_providers/text_generation/gemini_pro_text.py

@@ -2,6 +2,7 @@
 import os
 import sys
 from pathlib import Path
+import streamlit as st
 
 import google.generativeai as genai
 from dotenv import load_dotenv
@@ -44,6 +45,7 @@ def gemini_text_response(prompt, temperature, top_p, n, max_tokens):
             for chunk in response:
                 # text_response.append(chunk.text)
                 print(chunk.text)
+                #st.write(chunk.text)
         else:
             print(response)
         logger.info(f"Number of Token in Prompt Sent: {model.count_tokens(prompt)}")

lib/workspace/alwrity_ui_styling.css

@@ -95,7 +95,7 @@ input[type="text"] {
 }
 
 /* Custom button styling */
-button {
+div.stButton > button:first-child {
     background: #1565C0;  /* Match tab color */
     color: white;
     border: none;
@@ -112,8 +112,8 @@ button {
     font-weight: bold;
 }
 
-button:hover {
-    background-color: #1976D2;  /* Match tab hover color */
+div.stButton > button:hover:first-child {
+    background-color: #1976A2;  /* Match tab hover color */
     box-shadow: 2px 2px 8px rgba(0, 0, 0, 0.3);
 }