Merge pull request #3 from beautiful-code/feature/add-streamlit-ui

agents/article_evaluator.py

@@ -1,5 +1,6 @@
 from crewai import Agent
 from llms.gpt import llm
+from tools.helpers import streamlit_callback
 
 article_evaluator = Agent(
     role="Recommended Article Evaluator",
@@ -14,5 +15,6 @@ article_evaluator = Agent(
         "incremental learning once the user completes reading the articles."
     ),
     allow_delegation=False,
-    llm=llm
+    llm=llm,
+    step_callback=streamlit_callback
 )

agents/curiosity_catalyst.py

@@ -1,5 +1,6 @@
 from crewai import Agent
 from llms.gpt import llm
+from tools.helpers import streamlit_callback
 from tools.scrape_website import scrape_tool
 
 curiosity_catalyst = Agent(
@@ -12,5 +13,6 @@ curiosity_catalyst = Agent(
     "for reading the articles."
   ),
   allow_delegation=False,
-  llm=llm
+  llm=llm,
+  step_callback=streamlit_callback
 )

agents/learning_curator.py

@@ -1,7 +1,8 @@
 from crewai import Agent
+from llms.gpt import llm
+from tools.helpers import streamlit_callback
 from tools.scrape_website import scrape_tool
 from tools.search_web import search_tool
-from llms.gpt import llm
 
 learning_curator = Agent(
     role="Personal Learning Curator",
@@ -14,5 +15,6 @@ learning_curator = Agent(
     ),
     allow_delegation=False,
     tools=[scrape_tool, search_tool],
-    llm=llm
+    llm=llm,
+    step_callback=streamlit_callback
 )

agents/learning_profiler.py

@@ -1,6 +1,7 @@
 from crewai import Agent
-from tools.scrape_website import scrape_tool
 from llms.gpt import llm
+from tools.helpers import streamlit_callback
+from tools.scrape_website import scrape_tool
 
 learning_profiler = Agent(
     role="Personal Learning Profiler",
@@ -11,5 +12,7 @@ learning_profiler = Agent(
       "The profile you build gives a high level overview of what interests that the user has. "
     ),
     allow_delegation=False,
-    llm=llm
+    OPENAI_API_KEY="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",
+    llm=llm,
+    step_callback=streamlit_callback
 )

app.py

@@ -1,31 +1,91 @@
-from dotenv import load_dotenv
-load_dotenv()
+import json
+import streamlit as st
 
-from crew.article_suggestion import article_recommendation_crew
 import utils.settings as settings
+
+from crew.article_suggestion import article_recommendation_crew
+from dotenv import load_dotenv
 from utils.write_to_json import write_dict_to_json as write_dict_to_json
 
 settings.init()
 
-result = article_recommendation_crew.kickoff(inputs={
-  "interests": "Ruby On Rails, Architecture, Go Lang",
-  "previous_article_insights":
+load_dotenv(
+    "/home/quizra/Documents/Learning_practise/python/streamlit/growthi-app/growthy_agents/.env"
+)
+
+
+def icon(emoji: str):
+    """Shows an emoji as a Notion-style page icon."""
+    st.write(
+        f'<span style="font-size: 78px; line-height: 1">{emoji}</span>',
+        unsafe_allow_html=True,
+    )
+
+
+st.set_page_config(layout="wide")
+
+
+def main():
+    icon("📖 Articles RecommendAIgent")
+    st.subheader("Let AI agents recommend articles based on your interest!")
+
+    with st.sidebar:
+        st.header("👇 Provide Your Interests Below!")
+        with st.form("user_input_form", border=True):
+            interests = st.text_input(
+                "Enter your interests (comma-separated):",
+                "GenAI, Architecture, Agentic Programming",
+            )
+            previous_article_insights = st.text_area(
+                "Enter previous article insights:",
+                "Agentic Design Patterns (https://www.deeplearning.ai/the-batch/how-agents-can-improve-llm-performance/)\n"
+                "Reflection: The LLM examines its own work to come up with ways to improve it. "
+                "Tool Use: The LLM is given tools such as web search, code execution, or any other function to help it gather information, take action, or process data. "
+                "Planning: The LLM comes up with, and executes, a multistep plan to achieve a goal "
+                "Multi-agent collaboration: More than one AI agent work together, splitting up tasks and discussing and debating ideas, to come up with better solutions than a single agent would.\n\n"
+                # "GenAI Multi-Agent Systems (https://thenewstack.io/genai-multi-agent-systems-a-secret-weapon-for-tech-teams/)\n"
+                "Multi-agent systems go beyond the task-oriented roles to truly super-charge development and strategy teams. "
+                "Successful multi-agent systems act as a “digital twin” for your development team. "
+                "Different Approaches: 1. Centralized, with one agent in the center that collects and assimilates all the other outputs. "
+                "2. Distributed, where there is no central controller and the agents coordinate directly with one another in an “agent swarm. "
+                "3. Hierarchical, where agents are organized in teams or hierarchical layers.\n",
+                height=400,
+            )
+            st.markdown("")  # Adding a blank space here
+            submitted = st.form_submit_button("Submit")
+
+    if submitted:
+        with st.status(
+            "🤖 **Agents at work...**", state="running", expanded=True
+        ) as status:
+            with st.container(height=500, border=False):
+                result = article_recommendation_crew.kickoff(
+                    inputs={
+                        "interests": interests,
+                        "previous_article_insights": previous_article_insights,
+                    }
+                )
+            status.update(
+                label="✅ Articles are Ready for Reading!",
+                state="complete",
+                expanded=False,
+            )
+
+        st.subheader("", anchor=False, divider="rainbow")
 
-  "Agentic Design Patterns (https://www.deeplearning.ai/the-batch/how-agents-can-improve-llm-performance/)\n"
-  "Reflection: The LLM examines its own work to come up with ways to improve it. "
-  "Tool Use: The LLM is given tools such as web search, code execution, or any other function to help it gather information, take action, or process data. "
-  "Planning: The LLM comes up with, and executes, a multistep plan to achieve a goal "
-  "Multi-agent collaboration: More than one AI agent work together, splitting up tasks and discussing and debating ideas, to come up with better solutions than a single agent would.\n\n"
+        json_data = json.loads(result)
+        articles_list = json_data.get("articles", None)
 
-  "GenAI Multi-Agent Systems (https://thenewstack.io/genai-multi-agent-systems-a-secret-weapon-for-tech-teams/)\n"
-  "Multi-agent systems go beyond the task-oriented roles to truly super-charge development and strategy teams. "
-  "Successful multi-agent systems act as a “digital twin” for your development team. "
-  "Different Approaches: 1. Centralized, with one agent in the center that collects and assimilates all the other outputs. "
-  "2. Distributed, where there is no central controller and the agents coordinate directly with one another in an “agent swarm. "
-  "3. Hierarchical, where agents are organized in teams or hierarchical layers.\n"
-})
+        if articles_list is None:
+            st.markdown("No articles found.")
+            return
+        else:
+            for article in articles_list:
+                st.markdown(f"# {article['title']}")
+                st.markdown(f"**URL:** [{article['url']}]({article['url']})")
+                st.markdown(f"**Pitch:** {article['pitch']}")
+                st.markdown("---")
 
-print(result)
-print("Usage Metrics:\n", article_recommendation_crew.usage_metrics)
 
-write_dict_to_json(settings.articles, filename="final_articles.json")
+if __name__ == "__main__":
+    main()

crew/article_suggestion.py

@@ -1,4 +1,5 @@
 from crewai import Crew
+from llms.gpt import llm
 from agents.learning_profiler import learning_profiler
 from agents.learning_curator import learning_curator
 from agents.article_evaluator import article_evaluator
@@ -7,7 +8,6 @@ from tasks.create_learning_profile import learning_profile_task
 from tasks.new_article_suggestion import article_suggestion_task
 from tasks.evaluate_articles import evaluation_task
 from tasks.create_article_pitch import article_pitch_task
-from llms.gpt import llm
 
 article_recommendation_crew = Crew(
     agents=[learning_profiler, learning_curator,
@@ -23,4 +23,5 @@ article_recommendation_crew = Crew(
                     "model": 'text-embedding-3-small'
         }
     }
+    # manager_llm=gemini_client
 )

llms/gemini.py

@@ -1,3 +1,11 @@
+import asyncio
 from langchain_google_genai import ChatGoogleGenerativeAI
 
+try:
+    # Check if there's already a running event loop
+    asyncio.get_event_loop()
+except RuntimeError:
+    # If not, create a new event loop
+    asyncio.set_event_loop(asyncio.new_event_loop())
+
 llm=ChatGoogleGenerativeAI(model="gemini-1.5-flash",verbose=True)

tasks/create_article_pitch.py

@@ -1,11 +1,15 @@
+import json
+import streamlit as st
+
+import utils.settings as settings
+
 from crewai import Task
-from agents.curiosity_catalyst import curiosity_catalyst
-from tools.scrape_website import scrape_tool
 from crewai.tasks.task_output import TaskOutput
-import utils.settings as settings
 from pydantic import BaseModel
 from typing import List
-import json
+
+from agents.curiosity_catalyst import curiosity_catalyst
+from tools.scrape_website import scrape_tool
 
 
 class PitchedArticle(BaseModel):
@@ -19,10 +23,11 @@ class PitchedArticles(BaseModel):
 
 
 def callback_function(output: TaskOutput):
-    evaluated_articles = json.loads(output.exported_output)['articles']
-
-    for article in evaluated_articles:
-        settings.articles[article['url']]['pitch'] = article['pitch']
+    # evaluated_articles = json.loads(output.exported_output)['articles']
+    # st.markdown(evaluated_articles)
+    # for article in evaluated_articles:
+    #     settings.articles[article['url']]['pitch'] = article['pitch']
+    st.markdown("### Create Article Pitch is executed successfully!")
 
 
 article_pitch_task = Task(

tasks/create_learning_profile.py

@@ -1,8 +1,13 @@
+import json
+import streamlit as st
+
 from crewai import Task
-from agents.learning_profiler import learning_profiler
+from crewai.tasks.task_output import TaskOutput
 from pydantic import BaseModel
 from typing import List
 
+from agents.learning_profiler import learning_profiler
+
 
 class Topic(BaseModel):
     name: str
@@ -12,7 +17,9 @@ class Topic(BaseModel):
 class LearningProfile(BaseModel):
     topics_of_interests: List[str]
     learnings: List[Topic]
-
+    
+def callback_function(output: TaskOutput):
+    st.markdown("### Create Learning Profile task is executed successfully!")
 
 learning_profile_task = Task(
     description=(
@@ -27,5 +34,6 @@ learning_profile_task = Task(
     agent=learning_profiler,
     output_json=LearningProfile,
     output_file="learning_profile.json",
-    async_execution=False
+    async_execution=False,
+    callback=callback_function
 )

tasks/evaluate_articles.py

@@ -1,10 +1,14 @@
+import json
+import streamlit as st
+
+import utils.settings as settings
+
 from crewai import Task
-from agents.article_evaluator import article_evaluator
 from crewai.tasks.task_output import TaskOutput
-import utils.settings as settings
 from pydantic import BaseModel
 from typing import List
-import json
+
+from agents.article_evaluator import article_evaluator
 
 
 class EvaluatedArticle(BaseModel):
@@ -19,13 +23,14 @@ class EvaluatedArticles(BaseModel):
 
 
 def callback_function(output: TaskOutput):
-    evaluated_articles = json.loads(output.exported_output)['articles']
-
-    for article in evaluated_articles:
-        settings.articles[article['url']
-                          ]['evaluation_score'] = article['evaluation_score']
-        settings.articles[article['url']
-                          ]['evaluation_reason'] = article['evaluation_reason']
+    # evaluated_articles = json.loads(output.exported_output)['articles']
+
+    # for article in evaluated_articles:
+    #     settings.articles[article['url']
+    #                       ]['evaluation_score'] = article['evaluation_score']
+    #     settings.articles[article['url']
+    #                       ]['evaluation_reason'] = article['evaluation_reason']
+    st.markdown("### Evaluate Articles task is executed successfully!")
 
 
 evaluation_task = Task(

tasks/new_article_suggestion.py

@@ -1,10 +1,14 @@
+import json
+import streamlit as st
+
+import utils.settings as settings
+
 from crewai import Task
-from agents.learning_curator import learning_curator
 from crewai.tasks.task_output import TaskOutput
-import utils.settings as settings
 from pydantic import BaseModel
 from typing import List
-import json
+
+from agents.learning_curator import learning_curator
 
 
 class SuggestedArticle(BaseModel):
@@ -22,6 +26,7 @@ def callback_function(output: TaskOutput):
 
     for article in suggested_articles:
         settings.articles[article['url']] = article
+    st.markdown("### New Article Suggestion task is executed successfully!")
 
 
 article_suggestion_task = Task(

tools/helpers.py

@@ -0,0 +1,45 @@
+import streamlit as st
+from crewai.tasks.task_output import TaskOutput
+
+def streamlit_callback(step_output:TaskOutput):
+    st.markdown("---")
+    for step in step_output:
+        if isinstance(step, tuple) and len(step) == 2:
+            action, observation = step
+
+            # Display action information
+            if isinstance(action, dict) and all(key in action for key in ["tool", "tool_input", "log"]):
+                st.markdown(f"**Tool:** {action['tool']}")
+                st.markdown(f"**Tool Input:** {action['tool_input']}")
+                st.markdown(f"**Log:** {action['log']}")
+                if "Action" in action:
+                    st.markdown(f"# 📝 Processing Action...")
+                    st.markdown(f"**Action:** {action['Action']}")
+                st.markdown(f"**Action Input:** ```json\n{action['tool_input']}\n```")
+            elif isinstance(action, str):
+                if action != 'log':
+                    continue
+                st.markdown(f"# Action Result...")
+                st.markdown(f"**Action:** {action}")
+            else:
+                st.markdown(f"**Action:** {str(action)}")
+
+            # Display observation information
+            st.markdown(f"**Thought**")
+            if isinstance(observation, str):
+                observation_lines = observation.split('\n')
+                for line in observation_lines:
+                    if line.startswith('Title: '):
+                        st.markdown(f"**Title:** {line[7:]}")
+                    elif line.startswith('Link: '):
+                        st.markdown(f"**Link:** {line[6:]}")
+                    elif line.startswith('Snippet: '):
+                        st.markdown(f"**Snippet:** {line[9:]}")
+                    elif line.startswith('-'):
+                        st.markdown(line)
+                    else:
+                        st.markdown(line)
+            else:
+                st.markdown(str(observation))
+        else:
+            st.markdown(step)