kunthawat/ALwrity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

WIP - Streamlit UI, firecrawl - V0.5

Browse Source
This commit is contained in:
ajaysi
2024-06-12 16:01:46 +05:30
parent ccbaa0e4fa
commit f2aa79264e
12 changed files with 201 additions and 261 deletions
Download Patch File Download Diff File Expand all files Collapse all files

100
lib/ai_writers/web_url_ai_writer.py
View File

@@ -1,6 +1,8 @@
import sys
import os
from textwrap import dedent
import json
from pathlib import Path
from datetime import datetime
import streamlit as st
@@ -14,14 +16,11 @@ logger.add(sys.stdout,
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
)
from ..ai_web_researcher.gpt_online_researcher import do_google_serp_search,\
do_tavily_ai_search, do_metaphor_ai_research, do_google_pytrends_analysis
from ..ai_web_researcher.firecrawl_web_crawler import scrape_url
from .blog_from_google_serp import write_blog_google_serp, blog_with_research
from ..ai_web_researcher.you_web_reseacher import get_rag_results, search_ydc_index
from ..blog_metadata.get_blog_metadata import blog_metadata
from ..blog_postprocessing.save_blog_to_file import save_blog_to_file
from ..gpt_providers.text_to_image_generation.main_generate_image_from_prompt import generate_image
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
def blog_from_url(weburl):
@@ -38,62 +37,36 @@ def blog_from_url(weburl):
with st.status("Started Writing..", expanded=True) as status:
st.empty()
status.update(label=f"Researching and Writing Blog on: {weburl}")
scraped_text = scrape_url(weburl)
print(scraped_text)
exit(1)
# Call on the got-researcher, tavily apis for this. Do google search for organic competition.
try:
google_search_result, g_titles = do_google_serp_search(search_keywords)
status.update(label=f"🙎 Finished with Google web for Search: {search_keywords}")
example_blog_titles.append(g_titles)
status.update(label=f"🛀 Starting Tavily AI research: {search_keywords}")
tavily_search_result, t_titles, t_answer = do_tavily_ai_search(search_keywords)
status.update(label=f"🙆 Finished Google Search & Tavily AI Search on: {search_keywords}",
state="complete", expanded=False)
scraped_text = scrape_url(weburl)
logger.info(scraped_text)
except Exception as err:
st.error(f"Failed in web research: {err}")
st.error(f"Failed to scrape web page from url-{weburl} - Error: {err}")
logger.error(f"Failed in web research: {err}")
st.stop()
status.update(label="Successfully Scraped/Fetched url: {weburl}", expanded=False, state="complete")
with st.status("Started Writing blog from google search..", expanded=True) as status:
status.update(label="Researching and Writing Blog on keywords.")
# Call on the got-researcher, tavily apis for this. Do google search for organic competition.
try:
status.update(label=f"🛀 Writing blog from Google Search on: {search_keywords}")
blog_markdown_str = write_blog_google_serp(search_keywords, google_search_result)
st.markdown(blog_markdown_str)
status.update(label="🙎 Draft 1: Your Content from Google search result.", state="complete", expanded=False)
except Exception as err:
st.error(f"Failed in Google web research: {err}")
logger.error(f"Failed in Google web research: {err}")
# logger.info/check the final blog content.
logger.info("######### Draft1: Finished Blog from Google web search: ###########")
with st.status("Started Writing blog from Tavily Web search..", expanded=True) as status:
with st.status(f"Started Writing blog from {weburl}..", expanded=True) as status:
# Do Tavily AI research to augument the above blog.
try:
#example_blog_titles.append(t_titles)
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}")
else:
print("Not Writing with TAVILY..\n\n")
blog_markdown_str = write_blog_from_weburl(scraped_text)
status.update(label="Finished Writing Blog From: {weburl}")
except Exception as err:
logger.error(f"Failed to do Tavily AI research: {err}")
logger.error(f"Failed to write blog from: {weburl}")
st.error(f"Failed to write blog from: {weburl}")
st.stop()
status.update(label="🙎 Generating - Title, Meta Description, Tags, Categories for the content.")
try:
status.update(label="🙎 Generating - Title, Meta Description, Tags, Categories for the content.")
blog_title, blog_meta_desc, blog_tags, blog_categories = blog_metadata(blog_markdown_str)
except Exception as err:
st.error(f"Failed to get blog metadata: {err}")
try:
status.update(label="🙎 Generating Image for the new blog.")
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)
@@ -106,8 +79,45 @@ def blog_from_url(weburl):
Meta description: {blog_meta_desc.replace(":", "-")}\n
---------------------------------------------------------------------\n
""")
logger.info(f"\n\n --------- Finished writing Blog for : {search_keywords} -------------- \n")
logger.info(f"\n\n --------- Finished writing Blog for : {weburl} -------------- \n")
st.markdown(f"{blog_frontmatter}")
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}")
def write_blog_from_weburl(scraped_website):
"""Combine the given online research and GPT blog content"""
try:
config_path = Path(os.environ["ALWRITY_CONFIG"])
with open(config_path, 'r', encoding='utf-8') as file:
config = json.load(file)
except Exception as err:
logger.error(f"Error: Failed to read values from config: {err}")
exit(1)
blog_characteristics = config['Blog Content Characteristics']
prompt = f"""
As expert Creative Content writer, I will provide you with scraped website content.
I want you to write a detailed {blog_characteristics['Blog Type']} blog post including 5 FAQs.
Below are the guidelines to follow:
1). You must respond in {blog_characteristics['Blog Language']} language.
2). Tone and Brand Alignment: Adjust your tone, voice, personality for {blog_characteristics['Blog Tone']} audience.
3). Make sure your response content length is of {blog_characteristics['Blog Length']} words.
4). Include FAQs from 'People also Ask' section of provided context 'google search result'.
I want the post to offer unique insights, relatable examples, and a fresh perspective on the topic.
\n\n
Website Content:
'''{scraped_website}'''
"""
logger.info("Generating blog and FAQs from Google web search results.")
try:
response = llm_text_gen(prompt)
return response
except Exception as err:
logger.error(f"Exit: Failed to get response from LLM: {err}")
exit(1)