Merge pull request #110 from Madhuvod/phidata-agno

Move phidata to Agno + few old error corrections

advanced_tools_frameworks/cursor_ai_experiments/requirements.txt

@@ -0,0 +1,7 @@
+scrapegraphai
+playwright
+langchain-community
+streamlit-chat
+streamlit
+crewai
+ollama

advanced_tools_frameworks/llm_router_app/requirements.txt

@@ -1,2 +1,3 @@
 streamlit
-"routellm[serve,eval]"
+"routellm[serve,eval]"
+routellm

advanced_tools_frameworks/local_llama3.1_tool_use/llama3_tool_use.py

@@ -1,9 +1,9 @@
 import streamlit as st
 import os
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.llm.ollama import Ollama
+from agno.models.ollama import Ollama
-from phi.tools.yfinance import YFinanceTools
+from agno.tools.yfinance import YFinanceTools
-from phi.tools.serpapi_tools import SerpApiTools
+from agno.tools.serpapi import SerpApiTools
 
 st.set_page_config(page_title="Llama-3 Tool Use", page_icon="🦙")
 
@@ -13,9 +13,9 @@ if 'SERPAPI_API_KEY' not in os.environ:
     st.stop()
 
 def get_assistant(tools):
-    return Assistant(
+    return Agent(
         name="llama3_assistant",
-        llm=Ollama(model="llama3"),
+        model=Ollama(id="llama3.1:8b"),
         tools=tools,
         description="You are a helpful assistant that can access specific tools based on user selection.",
         show_tool_calls=True,
@@ -25,7 +25,7 @@ def get_assistant(tools):
 
     )
 
-st.title("🦙 Local Llama-3 Tool Use")
+st.title("🦙 Local Llama-3.1 Tool Use")
 st.markdown("""
 This app demonstrates function calling with the local Llama3 model using Ollama.
 Select tools in the sidebar and ask relevant questions!

advanced_tools_frameworks/local_llama3.1_tool_use/requirements.txt

@@ -1,3 +1,3 @@
 streamlit 
 ollama 
-phidata
+agno

advanced_tools_frameworks/web_search_ai_assistant/claude_websearch.py

@@ -1,8 +1,8 @@
 # Import the required libraries
 import streamlit as st
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
-from phi.llm.anthropic import Claude
+from agno.models.anthropic import Claude
 
 # Set up the Streamlit app
 st.title("Claude Sonnet + AI Web Search 🤖")
@@ -13,12 +13,12 @@ anthropic_api_key = st.text_input("Anthropic's Claude API Key", type="password")
 
 # If Anthropic API key is provided, create an instance of Assistant
 if anthropic_api_key:
-    assistant = Assistant(
+    assistant = Agent(
-    llm=Claude(
+    model=Claude(
-        model="claude-3-5-sonnet-20240620",
+        id="claude-3-5-sonnet-20240620",
         max_tokens=1024,
-        temperature=0.9,
+        temperature=0.3,
-        api_key=anthropic_api_key) , tools=[DuckDuckGo()], show_tool_calls=True
+        api_key=anthropic_api_key) , tools=[DuckDuckGoTools()], show_tool_calls=True
     )
     # Get the search query from the user
     query= st.text_input("Enter the Search Query", type="default")
@@ -26,4 +26,4 @@ if anthropic_api_key:
     if query:
         # Search the web using the AI Assistant
         response = assistant.run(query, stream=False)
-        st.write(response)
+        st.write(response.content)

advanced_tools_frameworks/web_search_ai_assistant/gpt4_websearch.py

@@ -1,8 +1,8 @@
 # Import the required libraries
 import streamlit as st
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
-from phi.llm.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
 
 # Set up the Streamlit app
 st.title("AI Web Search Assistant 🤖")
@@ -14,12 +14,12 @@ openai_access_token = st.text_input("OpenAI API Key", type="password")
 # If OpenAI API key is provided, create an instance of Assistant
 if openai_access_token:
     # Create an instance of the Assistant
-    assistant = Assistant(
+    assistant = Agent(
-    llm=OpenAIChat(
+    model=OpenAIChat(
-        model="gpt-4o",
+        id="gpt-4o",
         max_tokens=1024,
         temperature=0.9,
-        api_key=openai_access_token) , tools=[DuckDuckGo()], show_tool_calls=True
+        api_key=openai_access_token) , tools=[DuckDuckGoTools()], show_tool_calls=True
     )
 
     # Get the search query from the user
@@ -28,4 +28,4 @@ if openai_access_token:
     if query:
         # Search the web using the AI Assistant
         response = assistant.run(query, stream=False)
-        st.write(response)
+        st.write(response.content)

advanced_tools_frameworks/web_search_ai_assistant/requirements.txt

@@ -1,4 +1,4 @@
 streamlit
 openai
-phidata
+agno
 duckduckgo-search

ai_agent_tutorials/ai_data_analysis_agent/README.md

@@ -1,6 +1,6 @@
 # 📊 AI Data Analysis Agent
 
-An AI data analysis Agent built using the phidata Agent framework and Openai's gpt-4o model. This agent helps users analyze their data - csv, excel files through natural language queries, powered by OpenAI's language models and DuckDB for efficient data processing - making data analysis accessible to users regardless of their SQL expertise.
+An AI data analysis Agent built using the Agno Agent framework and Openai's gpt-4o model. This agent helps users analyze their data - csv, excel files through natural language queries, powered by OpenAI's language models and DuckDB for efficient data processing - making data analysis accessible to users regardless of their SQL expertise.
 
 ## Features
 

ai_agent_tutorials/ai_data_analysis_agent/ai_data_analyst.py

@@ -3,9 +3,9 @@ import tempfile
 import csv
 import streamlit as st
 import pandas as pd
-from phi.model.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
 from phi.agent.duckdb import DuckDbAgent
-from phi.tools.pandas import PandasTools
+from agno.tools.pandas import PandasTools
 import re
 
 # Function to preprocess and save the uploaded file

ai_agent_tutorials/ai_data_analysis_agent/requirements.txt

@@ -1,6 +1,7 @@
-phidata==2.7.3
+phidata
 streamlit==1.41.1
 openai==1.58.1
 duckdb==1.1.3
 pandas
-numpy==1.26.4
+numpy==1.26.4
+agno

ai_agent_tutorials/ai_finance_agent_team/finance_agent_team.py

@@ -1,16 +1,16 @@
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
-from phi.storage.agent.sqlite import SqlAgentStorage
+from agno.storage.agent.sqlite import SqliteAgentStorage
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
-from phi.tools.yfinance import YFinanceTools
+from agno.tools.yfinance import YFinanceTools
-from phi.playground import Playground, serve_playground_app
+from agno.playground import Playground, serve_playground_app
 
 web_agent = Agent(
     name="Web Agent",
     role="Search the web for information",
     model=OpenAIChat(id="gpt-4o"),
-    tools=[DuckDuckGo()],
+    tools=[DuckDuckGoTools()],
-    storage=SqlAgentStorage(table_name="web_agent", db_file="agents.db"),
+    storage=SqliteAgentStorage(table_name="web_agent", db_file="agents.db"),
     add_history_to_messages=True,
     markdown=True,
 )
@@ -21,7 +21,7 @@ finance_agent = Agent(
     model=OpenAIChat(id="gpt-4o"),
     tools=[YFinanceTools(stock_price=True, analyst_recommendations=True, company_info=True, company_news=True)],
     instructions=["Always use tables to display data"],
-    storage=SqlAgentStorage(table_name="finance_agent", db_file="agents.db"),
+    storage=SqliteAgentStorage(table_name="finance_agent", db_file="agents.db"),
     add_history_to_messages=True,
     markdown=True,
 )

ai_agent_tutorials/ai_finance_agent_team/requirements.txt

@@ -1,5 +1,5 @@
 openai
-phidata
+agno
 duckduckgo-search
 yfinance
 fastapi[standard] 

ai_agent_tutorials/ai_health_fitness_agent/README.md

@@ -1,6 +1,6 @@
 # AI Health & Fitness Planner Agent 🏋️‍♂️
 
-The **AI Health & Fitness Planner** is a personalized health and fitness Agent powered by Phidata's AI Agent framework. This app generates tailored dietary and fitness plans based on user inputs such as age, weight, height, activity level, dietary preferences, and fitness goals.
+The **AI Health & Fitness Planner** is a personalized health and fitness Agent powered by Agno AI Agent framework. This app generates tailored dietary and fitness plans based on user inputs such as age, weight, height, activity level, dietary preferences, and fitness goals.
 
 ## Features
 
@@ -24,7 +24,7 @@ The **AI Health & Fitness Planner** is a personalized health and fitness Agent p
 
 The application requires the following Python libraries:
 
-- `phidata`
+- `agno`
 - `google-generativeai`
 - `streamlit`
 

ai_agent_tutorials/ai_health_fitness_agent/health_agent.py

@@ -1,6 +1,6 @@
 import streamlit as st
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.google import Gemini
+from agno.models.google import Gemini
 
 st.set_page_config(
     page_title="AI Health & Fitness Planner",

ai_agent_tutorials/ai_health_fitness_agent/requirements.txt

@@ -1,3 +1,3 @@
-phidata==2.5.33
 google-generativeai==0.8.3
-streamlit==1.40.2
+streamlit==1.40.2
+agno

ai_agent_tutorials/ai_investment_agent/README.md

@@ -1,5 +1,5 @@
 ## 📈 AI Investment Agent
-This Streamlit app is an AI-powered investment agent that compares the performance of two stocks and generates detailed reports. By using GPT-4o with Yahoo Finance data, this app provides valuable insights to help you make informed investment decisions.
+This Streamlit app is an AI-powered investment agent built with Agno's AI Agent framework that compares the performance of two stocks and generates detailed reports. By using GPT-4o with Yahoo Finance data, this app provides valuable insights to help you make informed investment decisions.
 
 ### Features
 - Compare the performance of two stocks
@@ -32,7 +32,7 @@ streamlit run investment_agent.py
 ### How it Works?
 
 - Upon running the app, you will be prompted to enter your OpenAI API key. This key is used to authenticate and access the OpenAI language model.
-- Once you provide a valid API key, an instance of the Assistant class is created. This assistant utilizes the GPT-4 language model from OpenAI and the YFinanceTools for accessing stock data.
+- Once you provide a valid API key, an instance of the Assistant class is created. This assistant utilizes the GPT-4o language model from OpenAI and the YFinanceTools for accessing stock data.
 - Enter the stock symbols of the two companies you want to compare in the provided text input fields.
 - The assistant will perform the following steps:
     - Retrieve real-time stock prices and historical data using YFinanceTools

ai_agent_tutorials/ai_investment_agent/investment_agent.py

@@ -1,8 +1,8 @@
 # Import the required libraries
 import streamlit as st
-from phi.assistant import Assistant
+from agno.agent import Assistant
-from phi.llm.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
-from phi.tools.yfinance import YFinanceTools
+from agno.tools.yfinance import YFinanceTools
 
 # Set up the Streamlit app
 st.title("AI Investment Agent 📈🤖")
@@ -27,4 +27,4 @@ if openai_api_key:
         # Get the response from the assistant
         query = f"Compare {stock1} to {stock2}. Use every tool you have."
         response = assistant.run(query, stream=False)
-        st.write(response)
+        st.write(response.content)

ai_agent_tutorials/ai_investment_agent/requirements.txt

@@ -1,4 +1,4 @@
 streamlit 
-phidata
+agno
 openai
 yfinance

ai_agent_tutorials/ai_journalist_agent/journalist_agent.py

@@ -1,10 +1,10 @@
 # Import the required libraries
 from textwrap import dedent
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.tools.serpapi_tools import SerpApiTools
+from agno.tools.serpapi import SerpApiTools
-from phi.tools.newspaper4k import Newspaper4k as NewspaperToolkit
+from agno.tools.newspaper4k import Newspaper4kTools
 import streamlit as st
-from phi.llm.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
 
 # Set up the Streamlit app
 st.title("AI Journalist Agent 🗞️")
@@ -17,10 +17,10 @@ openai_api_key = st.text_input("Enter OpenAI API Key to access GPT-4o", type="pa
 serp_api_key = st.text_input("Enter Serp API Key for Search functionality", type="password")
 
 if openai_api_key and serp_api_key:
-    searcher = Assistant(
+    searcher = Agent(
         name="Searcher",
         role="Searches for top URLs based on a topic",
-        llm=OpenAIChat(model="gpt-4o", api_key=openai_api_key),
+        model=OpenAIChat(id="gpt-4o", api_key=openai_api_key),
         description=dedent(
             """\
         You are a world-class journalist for the New York Times. Given a topic, generate a list of 3 search terms
@@ -37,10 +37,10 @@ if openai_api_key and serp_api_key:
         tools=[SerpApiTools(api_key=serp_api_key)],
         add_datetime_to_instructions=True,
     )
-    writer = Assistant(
+    writer = Agent(
         name="Writer",
         role="Retrieves text from URLs and writes a high-quality article",
-        llm=OpenAIChat(model="gpt-4o", api_key=openai_api_key),
+        model=OpenAIChat(id="gpt-4o", api_key=openai_api_key),
         description=dedent(
             """\
         You are a senior writer for the New York Times. Given a topic and a list of URLs,
@@ -57,15 +57,14 @@ if openai_api_key and serp_api_key:
             "Focus on clarity, coherence, and overall quality.",
             "Never make up facts or plagiarize. Always provide proper attribution.",
         ],
-        tools=[NewspaperToolkit()],
+        tools=[Newspaper4kTools()],
         add_datetime_to_instructions=True,
-        add_chat_history_to_prompt=True,
+        markdown=True,
-        num_history_messages=3,
     )
 
-    editor = Assistant(
+    editor = Agent(
         name="Editor",
-        llm=OpenAIChat(model="gpt-4o", api_key=openai_api_key),
+        model=OpenAIChat(id="gpt-4o", api_key=openai_api_key),
         team=[searcher, writer],
         description="You are a senior NYT editor. Given a topic, your goal is to write a NYT worthy article.",
         instructions=[
@@ -88,4 +87,4 @@ if openai_api_key and serp_api_key:
         with st.spinner("Processing..."):
             # Get the response from the assistant
             response = editor.run(query, stream=False)
-            st.write(response)
+            st.write(response.content)

ai_agent_tutorials/ai_journalist_agent/requirements.txt

@@ -1,5 +1,5 @@
 streamlit 
-phidata
+agno
 openai
 google-search-results 
 newspaper4k 

ai_agent_tutorials/ai_lead_generation_agent/ai_lead_generation_agent.py

@@ -1,8 +1,8 @@
 import streamlit as st
 import requests
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.tools.firecrawl import FirecrawlTools
+from agno.tools.firecrawl import FirecrawlTools
-from phi.model.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
 from firecrawl import FirecrawlApp
 from pydantic import BaseModel, Field
 from typing import List

ai_agent_tutorials/ai_lead_generation_agent/requirements.txt

@@ -1,6 +1,6 @@
 firecrawl-py==1.9.0
-phidata==2.7.3
+agno
-composio-phidata==0.6.15
+composio-phidata
 composio==0.1.1
 pydantic==2.10.5
 streamlit

ai_agent_tutorials/ai_legal_agent_team/legal_agent_team.py

@@ -1,10 +1,10 @@
 import streamlit as st
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.knowledge.pdf import PDFKnowledgeBase, PDFReader
+from agno.knowledge.pdf import PDFKnowledgeBase, PDFReader
-from phi.vectordb.qdrant import Qdrant
+from agno.vectordb.qdrant import Qdrant
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
-from phi.model.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
-from phi.embedder.openai import OpenAIEmbedder
+from agno.embedder.openai import OpenAIEmbedder
 import tempfile
 import os
 
@@ -133,7 +133,7 @@ def main():
                             name="Legal Researcher",
                             role="Legal research specialist",
                             model=OpenAIChat(model="gpt-4o"),
-                            tools=[DuckDuckGo()],
+                            tools=[DuckDuckGoTools()],
                             knowledge=st.session_state.knowledge_base,
                             search_knowledge=True,
                             instructions=[

ai_agent_tutorials/ai_legal_agent_team/local_ai_legal_agent_team/local_legal_agent.py

@@ -1,9 +1,9 @@
 import streamlit as st
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.knowledge.pdf import PDFKnowledgeBase, PDFReader
+from agno.knowledge.pdf import PDFKnowledgeBase, PDFReader
-from phi.vectordb.qdrant import Qdrant
+from agno.vectordb.qdrant import Qdrant
-from phi.model.ollama import Ollama
+from agno.models.ollama import Ollama
-from phi.embedder.ollama import OllamaEmbedder
+from agno.embedder.ollama import OllamaEmbedder
 import tempfile
 import os
 

ai_agent_tutorials/ai_legal_agent_team/local_ai_legal_agent_team/requirements.txt

@@ -1,4 +1,4 @@
-phidata==2.6.7
+agno
 streamlit==1.40.2
 qdrant-client==1.12.1
 ollama==0.4.4

ai_agent_tutorials/ai_legal_agent_team/requirements.txt

@@ -1,4 +1,4 @@
-phidata==2.5.33       
+agno
 streamlit==1.40.2     
 qdrant-client==1.12.1         
 openai

ai_agent_tutorials/ai_medical_imaging_agent/README.md

@@ -1,6 +1,6 @@
 # 🩻 Medical Imaging Diagnosis Agent
 
-A Medical Imaging Diagnosis Agent build on phidata powered by Gemini 2.0 Flash Experimental that provides AI-assisted analysis of medical images of various scans. The agent acts as a medical imaging diagnosis expert to analyze various types of medical images and videos, providing detailed diagnostic insights and explanations.
+A Medical Imaging Diagnosis Agent build on agno powered by Gemini 2.0 Flash Experimental that provides AI-assisted analysis of medical images of various scans. The agent acts as a medical imaging diagnosis expert to analyze various types of medical images and videos, providing detailed diagnostic insights and explanations.
 
 ## Features
 

ai_agent_tutorials/ai_medical_imaging_agent/ai_medical_imaging.py

@@ -1,9 +1,9 @@
 import os
 from PIL import Image
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.google import Gemini
+from agno.models.google import Gemini
 import streamlit as st
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
 
 if "GOOGLE_API_KEY" not in st.session_state:
     st.session_state.GOOGLE_API_KEY = None
@@ -45,7 +45,7 @@ medical_agent = Agent(
         api_key=st.session_state.GOOGLE_API_KEY,
         id="gemini-2.0-flash-exp"
     ),
-    tools=[DuckDuckGo()],
+    tools=[DuckDuckGoTools()],
     markdown=True
 ) if st.session_state.GOOGLE_API_KEY else None
 

ai_agent_tutorials/ai_medical_imaging_agent/requirements.txt

@@ -1,5 +1,5 @@
 streamlit==1.40.2
-phidata==2.7.3
+agno
 Pillow==10.0.0
 duckduckgo-search==6.4.1
 google-generativeai==0.8.3

ai_agent_tutorials/ai_movie_production_agent/movie_production_agent.py

@@ -1,8 +1,8 @@
 # Import the required libraries
 import streamlit as st
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.tools.serpapi_tools import SerpApiTools
+from agno.tools.serpapi import SerpApiTools
-from phi.llm.anthropic import Claude
+from agno.models.anthropic import Claude
 from textwrap import dedent
 
 # Set up the Streamlit app
@@ -15,9 +15,9 @@ anthropic_api_key = st.text_input("Enter Anthropic API Key to access Claude Sonn
 serp_api_key = st.text_input("Enter Serp API Key for Search functionality", type="password")
 
 if anthropic_api_key and serp_api_key:
-    script_writer = Assistant(
+    script_writer = Agent(
         name="ScriptWriter",
-        llm=Claude(model="claude-3-5-sonnet-20240620", api_key=anthropic_api_key),
+        model=Claude(id="claude-3-5-sonnet-20240620", api_key=anthropic_api_key),
         description=dedent(
             """\
         You are an expert screenplay writer. Given a movie idea and genre, 
@@ -31,9 +31,9 @@ if anthropic_api_key and serp_api_key:
         ],
     )
 
-    casting_director = Assistant(
+    casting_director = Agent(
         name="CastingDirector",
-        llm=Claude(model="claude-3-5-sonnet-20240620", api_key=anthropic_api_key),
+        model=Claude(id="claude-3-5-sonnet-20240620", api_key=anthropic_api_key),
         description=dedent(
             """\
         You are a talented casting director. Given a script outline and character descriptions,
@@ -49,9 +49,9 @@ if anthropic_api_key and serp_api_key:
         tools=[SerpApiTools(api_key=serp_api_key)],
     )
 
-    movie_producer = Assistant(
+    movie_producer = Agent(
         name="MovieProducer",
-        llm=Claude(model="claude-3-5-sonnet-20240620", api_key=anthropic_api_key),
+        model=Claude(id="claude-3-5-sonnet-20240620", api_key=anthropic_api_key),
         team=[script_writer, casting_director],
         description="Experienced movie producer overseeing script and casting.",
         instructions=[

ai_agent_tutorials/ai_movie_production_agent/requirements.txt

@@ -1,5 +1,5 @@
 streamlit 
-phidata
+agno
 anthropic
 google-search-results  
 lxml_html_clean

ai_agent_tutorials/ai_personal_finance_agent/finance_agent.py

@@ -1,8 +1,8 @@
 from textwrap import dedent
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.tools.serpapi_tools import SerpApiTools
+from agno.tools.serpapi import SerpApiTools
 import streamlit as st
-from phi.llm.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
 
 # Set up the Streamlit app
 st.title("AI Personal Finance Planner 💰")
@@ -15,10 +15,10 @@ openai_api_key = st.text_input("Enter OpenAI API Key to access GPT-4o", type="pa
 serp_api_key = st.text_input("Enter Serp API Key for Search functionality", type="password")
 
 if openai_api_key and serp_api_key:
-    researcher = Assistant(
+    researcher = Agent(
         name="Researcher",
         role="Searches for financial advice, investment opportunities, and savings strategies based on user preferences",
-        llm=OpenAIChat(model="gpt-4o", api_key=openai_api_key),
+        model=OpenAIChat(id="gpt-4o", api_key=openai_api_key),
         description=dedent(
             """\
         You are a world-class financial researcher. Given a user's financial goals and current financial situation,
@@ -35,10 +35,10 @@ if openai_api_key and serp_api_key:
         tools=[SerpApiTools(api_key=serp_api_key)],
         add_datetime_to_instructions=True,
     )
-    planner = Assistant(
+    planner = Agent(
         name="Planner",
         role="Generates a personalized financial plan based on user preferences and research results",
-        llm=OpenAIChat(model="gpt-4o", api_key=openai_api_key),
+        model=OpenAIChat(id="gpt-4o", api_key=openai_api_key),
         description=dedent(
             """\
         You are a senior financial planner. Given a user's financial goals, current financial situation, and a list of research results,
@@ -54,8 +54,6 @@ if openai_api_key and serp_api_key:
             "Never make up facts or plagiarize. Always provide proper attribution.",
         ],
         add_datetime_to_instructions=True,
-        add_chat_history_to_prompt=True,
-        num_history_messages=3,
     )
 
     # Input fields for the user's financial goals and current financial situation
@@ -66,4 +64,4 @@ if openai_api_key and serp_api_key:
         with st.spinner("Processing..."):
             # Get the response from the assistant
             response = planner.run(f"Financial goals: {financial_goals}, Current situation: {current_situation}", stream=False)
-            st.write(response)
+            st.write(response.content)

ai_agent_tutorials/ai_personal_finance_agent/requirements.txt

@@ -1,4 +1,4 @@
 streamlit 
-phidata
+agno
 openai
 google-search-results

ai_agent_tutorials/ai_reasoning_agent/local_ai_reasoning_agent.py

@@ -1,6 +1,6 @@
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.ollama import Ollama
+from agno.models.ollama import Ollama
-from phi.playground import Playground, serve_playground_app
+from agno.playground import Playground, serve_playground_app
 
 reasoning_agent = Agent(name="Reasoning Agent", model=Ollama(id="qwq:32b"), markdown=True)
 

ai_agent_tutorials/ai_reasoning_agent/reasoning_agent.py

@@ -1,9 +1,9 @@
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
-from phi.cli.console import console
+from rich.console import Console
 
 regular_agent = Agent(model=OpenAIChat(id="gpt-4o-mini"), markdown=True)
-
+console = Console()
 reasoning_agent = Agent(
     model=OpenAIChat(id="gpt-4o"),
     reasoning=True,

ai_agent_tutorials/ai_recruitment_agent_team/ai_recruitment_agent_team.py

@@ -8,9 +8,9 @@ from datetime import datetime, timedelta
 import pytz
 
 import streamlit as st
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
-from phi.tools.email import EmailTools
+from agno.tools.email import EmailTools
 from phi.tools.zoom import ZoomTool
 from phi.utils.log import logger
 from streamlit_pdf_viewer import pdf_viewer

ai_agent_tutorials/ai_recruitment_agent_team/requirements.txt

@@ -1,5 +1,6 @@
 # Core dependencies
-phidata==2.7.3
+phidata
+agno
 streamlit==1.40.2
 PyPDF2==3.0.1
 streamlit-pdf-viewer==0.0.19

ai_agent_tutorials/ai_startup_trend_analysis_agent/requirements.txt

@@ -1,4 +1,4 @@
-phidata==2.5.33
+agno
 streamlit==1.40.2
 duckduckgo_search==6.3.7
 newspaper4k==0.9.3.1

ai_agent_tutorials/ai_startup_trend_analysis_agent/startup_trends_agent.py

@@ -1,9 +1,9 @@
 import streamlit as st
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
-from phi.model.anthropic import Claude
+from agno.models.anthropic import Claude
-from phi.tools.newspaper4k import Newspaper4k
+from agno.tools.newspaper4k import Newspaper4kTools
-from phi.tools import Tool
+from agno.tools import Tool
 import logging
 
 logging.basicConfig(level=logging.DEBUG)
@@ -25,7 +25,7 @@ if st.button("Generate Analysis"):
                 anthropic_model = Claude(id ="claude-3-5-sonnet-20240620",api_key=anthropic_api_key)
 
                 # Define News Collector Agent - Duckduckgo_search tool enables an Agent to search the web for information.
-                search_tool = DuckDuckGo(search=True, news=True, fixed_max_results=5)
+                search_tool = DuckDuckGoTools(search=True, news=True, fixed_max_results=5)
                 news_collector = Agent(
                     name="News Collector",
                     role="Collects recent news articles on the given topic",
@@ -37,7 +37,7 @@ if st.button("Generate Analysis"):
                 )
 
                 # Define Summary Writer Agent
-                news_tool = Newspaper4k(read_article=True, include_summary=True)
+                news_tool = Newspaper4kTools(read_article=True, include_summary=True)
                 summary_writer = Agent(
                     name="Summary Writer",
                     role="Summarizes collected news articles",

ai_agent_tutorials/ai_teaching_agent_team/requirements.txt

@@ -2,7 +2,7 @@ streamlit==1.41.1
 openai==1.58.1
 duckduckgo-search==6.4.1
 typing-extensions>=4.5.0
-phidata==2.7.3
+agno
 composio-phidata==0.6.9
 composio_core
 composio==0.1.1

ai_agent_tutorials/ai_teaching_agent_team/teaching_agent_team.py

@@ -1,11 +1,11 @@
 import streamlit as st
-from phi.agent import Agent, RunResponse
+from agno.agent import Agent, RunResponse
-from phi.model.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
 from composio_phidata import Action, ComposioToolSet
 import os
-from phi.tools.arxiv_toolkit import ArxivToolkit
+from agno.tools.arxiv import ArxivTools
-from phi.utils.pprint import pprint_run_response
+from agno.utils.pprint import pprint_run_response
-from phi.tools.serpapi_tools import SerpApiTools
+from agno.tools.serpapi import SerpApiTools
 
 # Set page configuration
 st.set_page_config(page_title="👨‍🏫 AI Teaching Agent Team", layout="centered")

ai_agent_tutorials/ai_tic_tac_toe_agent/README.md

@@ -1,6 +1,6 @@
 # 🎮 Agent X vs Agent O: Tic-Tac-Toe Game
 
-An interactive Tic-Tac-Toe game where two AI agents powered by different language models compete against each other built on phidata Agent Framework and Streamlit as UI. Watch as GPT-4O battles against either DeepSeek V3 or Google's Gemini 1.5 Flash in this classic game.
+An interactive Tic-Tac-Toe game where two AI agents powered by different language models compete against each other built on Agno Agent Framework and Streamlit as UI. Watch as GPT-4O battles against either DeepSeek V3 or Google's Gemini 1.5 Flash in this classic game.
 
 ## Features
 

ai_agent_tutorials/ai_tic_tac_toe_agent/ai_tic_tac_toe_agent.py

@@ -1,9 +1,9 @@
 import re
 import streamlit as st
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
-from phi.model.deepseek import DeepSeekChat
+from agno.models.deepseek import DeepSeek
-from phi.model.google import Gemini
+from agno.models.google import Gemini
 
 # Streamlit App Title
 st.title("🎮 Agent X vs Agent O: Tic-Tac-Toe Game")
@@ -122,7 +122,7 @@ if 'openai_api_key' in st.session_state:
     if 'deepseek_api_key' in st.session_state:
         player_o = Agent(
             name="Player O",
-            model=DeepSeekChat(api_key=st.session_state.deepseek_api_key),
+            model=DeepSeek(id="deepseek-chat", api_key=st.session_state.deepseek_api_key),
             instructions=[
                 "You are a Tic-Tac-Toe player using the symbol 'O'.",
                 "Your opponent is using the symbol 'X'. Block their potential winning moves.",

ai_agent_tutorials/ai_tic_tac_toe_agent/requirements.txt

@@ -1,4 +1,4 @@
 streamlit==1.41.1
-phidata==2.7.3
+agno
 openai==1.58.1
-google-generativeai==0.8.3
+google-generativeai==0.8.3

ai_agent_tutorials/ai_travel_agent/local_travel_agent.py

@@ -1,21 +1,21 @@
 from textwrap import dedent
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.tools.serpapi_tools import SerpApiTools
+from agno.tools.serpapi import SerpApiTools
 import streamlit as st
-from phi.llm.ollama import Ollama
+from agno.models.ollama import Ollama
 
 # Set up the Streamlit app
-st.title("AI Travel Planner using Llama-3 ✈️")
+st.title("AI Travel Planner using Llama-3.2 ✈️")
 st.caption("Plan your next adventure with AI Travel Planner by researching and planning a personalized itinerary on autopilot using local Llama-3")
 
 # Get SerpAPI key from the user
 serp_api_key = st.text_input("Enter Serp API Key for Search functionality", type="password")
 
 if serp_api_key:
-    researcher = Assistant(
+    researcher = Agent(
         name="Researcher",
         role="Searches for travel destinations, activities, and accommodations based on user preferences",
-        llm=Ollama(model="llama3:instruct", max_tokens=1024),
+        model=Ollama(id="llama3.2", max_tokens=1024),
         description=dedent(
             """\
         You are a world-class travel researcher. Given a travel destination and the number of days the user wants to travel for,
@@ -32,10 +32,10 @@ if serp_api_key:
         tools=[SerpApiTools(api_key=serp_api_key)],
         add_datetime_to_instructions=True,
     )
-    planner = Assistant(
+    planner = Agent(
         name="Planner",
         role="Generates a draft itinerary based on user preferences and research results",
-        llm=Ollama(model="llama3:instruct", max_tokens=1024),
+        model=Ollama(id="llama3.2", max_tokens=1024),
         description=dedent(
             """\
         You are a senior travel planner. Given a travel destination, the number of days the user wants to travel for, and a list of research results,
@@ -51,8 +51,6 @@ if serp_api_key:
             "Never make up facts or plagiarize. Always provide proper attribution.",
         ],
         add_datetime_to_instructions=True,
-        add_chat_history_to_prompt=True,
-        num_history_messages=3,
     )
 
     # Input fields for the user's destination and the number of days they want to travel for
@@ -63,4 +61,4 @@ if serp_api_key:
         with st.spinner("Processing..."):
             # Get the response from the assistant
             response = planner.run(f"{destination} for {num_days} days", stream=False)
-            st.write(response)
+            st.write(response.content)

ai_agent_tutorials/ai_travel_agent/requirements.txt

@@ -1,4 +1,4 @@
 streamlit 
-phidata
+agno
 openai
 google-search-results

ai_agent_tutorials/ai_travel_agent/travel_agent.py

@@ -1,8 +1,8 @@
 from textwrap import dedent
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.tools.serpapi_tools import SerpApiTools
+from agno.tools.serpapi import SerpApiTools
 import streamlit as st
-from phi.llm.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
 
 # Set up the Streamlit app
 st.title("AI Travel Planner ✈️")
@@ -15,10 +15,10 @@ openai_api_key = st.text_input("Enter OpenAI API Key to access GPT-4o", type="pa
 serp_api_key = st.text_input("Enter Serp API Key for Search functionality", type="password")
 
 if openai_api_key and serp_api_key:
-    researcher = Assistant(
+    researcher = Agent(
         name="Researcher",
         role="Searches for travel destinations, activities, and accommodations based on user preferences",
-        llm=OpenAIChat(model="gpt-4o", api_key=openai_api_key),
+        model=OpenAIChat(id="gpt-4o", api_key=openai_api_key),
         description=dedent(
             """\
         You are a world-class travel researcher. Given a travel destination and the number of days the user wants to travel for,
@@ -35,10 +35,10 @@ if openai_api_key and serp_api_key:
         tools=[SerpApiTools(api_key=serp_api_key)],
         add_datetime_to_instructions=True,
     )
-    planner = Assistant(
+    planner = Agent(
         name="Planner",
         role="Generates a draft itinerary based on user preferences and research results",
-        llm=OpenAIChat(model="gpt-4o", api_key=openai_api_key),
+        model=OpenAIChat(id="gpt-4o", api_key=openai_api_key),
         description=dedent(
             """\
         You are a senior travel planner. Given a travel destination, the number of days the user wants to travel for, and a list of research results,
@@ -54,8 +54,6 @@ if openai_api_key and serp_api_key:
             "Never make up facts or plagiarize. Always provide proper attribution.",
         ],
         add_datetime_to_instructions=True,
-        add_chat_history_to_prompt=True,
-        num_history_messages=3,
     )
 
     # Input fields for the user's destination and the number of days they want to travel for
@@ -66,4 +64,4 @@ if openai_api_key and serp_api_key:
         with st.spinner("Processing..."):
             # Get the response from the assistant
             response = planner.run(f"{destination} for {num_days} days", stream=False)
-            st.write(response)
+            st.write(response.content)

ai_agent_tutorials/gemini_multimodal_agent_demo/multimodal_ai_agent.py

@@ -1,11 +1,11 @@
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.google import Gemini
+from agno.models.google import Gemini
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
 from google.generativeai import upload_file, get_file
 import time
 
 # 1. Initialize the Multimodal Agent
-agent = Agent(model=Gemini(id="gemini-2.0-flash-exp"), tools=[DuckDuckGo()], markdown=True)
+agent = Agent(model=Gemini(id="gemini-2.0-flash-exp"), tools=[DuckDuckGoTools()], markdown=True)
 
 # 2. Image Input
 image_url = "https://example.com/sample_image.jpg"

ai_agent_tutorials/multi_agent_researcher/requirements.txt

@@ -1,3 +1,3 @@
 streamlit 
-phidata
+agno
 openai

ai_agent_tutorials/multi_agent_researcher/research_agent.py

@@ -1,8 +1,8 @@
 # Import the required libraries
 import streamlit as st
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.tools.hackernews import HackerNews
+from agno.tools.hackernews import HackerNewsTools
-from phi.llm.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
 
 # Set up the Streamlit app
 st.title("Multi-Agent AI Researcher 🔍🤖")
@@ -13,23 +13,23 @@ openai_api_key = st.text_input("OpenAI API Key", type="password")
 
 if openai_api_key:
     # Create instances of the Assistant
-    story_researcher = Assistant(
+    story_researcher = Agent(
         name="HackerNews Story Researcher",
         role="Researches hackernews stories and users.",
-        tools=[HackerNews()],
+        tools=[HackerNewsTools()],
     )
 
-    user_researcher = Assistant(
+    user_researcher = Agent(
         name="HackerNews User Researcher",
         role="Reads articles from URLs.",
-        tools=[HackerNews()],
+        tools=[HackerNewsTools()],
     )
 
-    hn_assistant = Assistant(
+    hn_assistant = Agent(
         name="Hackernews Team",
         team=[story_researcher, user_researcher],
-        llm=OpenAIChat(
+        model=OpenAIChat(
-            model="gpt-4o",
+            id="gpt-4o",
             max_tokens=1024,
             temperature=0.5,
             api_key=openai_api_key
@@ -42,4 +42,4 @@ if openai_api_key:
     if query:
         # Get the response from the assistant
         response = hn_assistant.run(query, stream=False)
-        st.write(response)
+        st.write(response.content)

ai_agent_tutorials/multi_agent_researcher/research_agent_llama3.py

@@ -1,32 +1,32 @@
 # Import the required libraries
 import streamlit as st
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.tools.hackernews import HackerNews
+from agno.tools.hackernews import HackerNews
-from phi.llm.ollama import Ollama
+from agno.models.ollama import Ollama
 
 # Set up the Streamlit app
 st.title("Multi-Agent AI Researcher using Llama-3 🔍🤖")
 st.caption("This app allows you to research top stories and users on HackerNews and write blogs, reports and social posts.")
 
 # Create instances of the Assistant
-story_researcher = Assistant(
+story_researcher = Agent(
     name="HackerNews Story Researcher",
     role="Researches hackernews stories and users.",
     tools=[HackerNews()],
-    llm=Ollama(model="llama3:instruct", max_tokens=1024)
+    model=Ollama(id="llama3.2", max_tokens=1024)
 )
 
-user_researcher = Assistant(
+user_researcher = Agent(
     name="HackerNews User Researcher",
     role="Reads articles from URLs.",
     tools=[HackerNews()],
-    llm=Ollama(model="llama3:instruct", max_tokens=1024)
+    model=Ollama(id="llama3.2", max_tokens=1024)
 )
 
-hn_assistant = Assistant(
+hn_assistant = Agent(
     name="Hackernews Team",
     team=[story_researcher, user_researcher],
-    llm=Ollama(model="llama3:instruct", max_tokens=1024)
+    model=Ollama(id="llama3.2", max_tokens=1024)
 )
 
 # Input field for the report query
@@ -35,4 +35,4 @@ query = st.text_input("Enter your report query")
 if query:
     # Get the response from the assistant
     response = hn_assistant.run(query, stream=False)
-    st.write(response)
+    st.write(response.content)

ai_agent_tutorials/multimodal_ai_agent/multimodal_reasoning_agent.py

@@ -1,6 +1,6 @@
 import streamlit as st
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.google import Gemini
+from agno.models.google import Gemini
 import tempfile
 import os
 

ai_agent_tutorials/multimodal_ai_agent/mutimodal_agent.py

@@ -1,7 +1,7 @@
 import streamlit as st
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.google import Gemini
+from agno.models.google import Gemini
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
 from google.generativeai import upload_file, get_file
 import time
 from pathlib import Path
@@ -21,7 +21,7 @@ def initialize_agent():
     return Agent(
         name="Multimodal Analyst",
         model=Gemini(id="gemini-2.0-flash-exp"),
-        tools=[DuckDuckGo()],
+        tools=[DuckDuckGoTools()],
         markdown=True,
     )
 

ai_agent_tutorials/multimodal_ai_agent/requirements.txt

@@ -1,3 +1,3 @@
-phidata==2.7.2
+agno
 google-generativeai==0.8.3
 streamlit==1.40.2

ai_agent_tutorials/multimodal_design_agent_team/design_agent_team.py

@@ -1,6 +1,6 @@
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.google import Gemini
+from agno.models.google import Gemini
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
 import streamlit as st
 from PIL import Image
 from typing import List, Optional
@@ -37,7 +37,7 @@ def initialize_agents(api_key: str) -> tuple[Agent, Agent, Agent]:
 
         market_agent = Agent(
             model=model,
-            tools=[DuckDuckGo(search=True)],
+            tools=[DuckDuckGoTools()],
             instructions=[
                 "You are a market research expert that:",
                 "1. Identifies market trends and competitor patterns",

ai_agent_tutorials/multimodal_design_agent_team/requirements.txt

@@ -1,6 +1,6 @@
 google-generativeai==0.8.3
 streamlit==1.41.1
-phidata==2.7.2
+agno
 Pillow==11.0.0
 duckduckgo-search==6.3.7
 

ai_agent_tutorials/xai_finance_agent/requirements.txt

@@ -1,4 +1,4 @@
-phidata
+agno
 duckduckgo-search
 yfinance
 fastapi[standard] 

ai_agent_tutorials/xai_finance_agent/xai_finance_agent.py

@@ -1,15 +1,15 @@
 # import necessary python libraries
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.xai import xAI
+from agno.models.xai import xAI
-from phi.tools.yfinance import YFinanceTools
+from agno.tools.yfinance import YFinanceTools
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
-from phi.playground import Playground, serve_playground_app
+from agno.playground import Playground, serve_playground_app
 
 # create the AI finance agent
 agent = Agent(
     name="xAI Finance Agent",
     model = xAI(id="grok-beta"),
-    tools=[DuckDuckGo(), YFinanceTools(stock_price=True, analyst_recommendations=True, stock_fundamentals=True)],
+    tools=[DuckDuckGoTools(), YFinanceTools(stock_price=True, analyst_recommendations=True, stock_fundamentals=True)],
     instructions = ["Always use tables to display financial/numerical data. For text data use bullet points and small paragrpahs."],
     show_tool_calls = True,
     markdown = True,

chat_with_X_tutorials/chat_with_pdf/requirements.txt

@@ -1,2 +1,3 @@
 streamlit
-embedchain
+embedchain
+streamlit-chat

chat_with_X_tutorials/chat_with_research_papers/chat_arxiv.py

@@ -1,8 +1,8 @@
 # Import the required libraries
 import streamlit as st
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.llm.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
-from phi.tools.arxiv_toolkit import ArxivToolkit
+from agno.tools.arxiv import ArxivTools
 
 # Set up the Streamlit app
 st.title("Chat with Research Papers 🔎🤖")
@@ -14,12 +14,12 @@ openai_access_token = st.text_input("OpenAI API Key", type="password")
 # If OpenAI API key is provided, create an instance of Assistant
 if openai_access_token:
     # Create an instance of the Assistant
-    assistant = Assistant(
+    assistant = Agent(
-    llm=OpenAIChat(
+    model=OpenAIChat(
-        model="gpt-4o",
+        id="gpt-4o",
         max_tokens=1024,
         temperature=0.9,
-        api_key=openai_access_token) , tools=[ArxivToolkit()]
+        api_key=openai_access_token) , tools=[ArxivTools()]
     )
 
     # Get the search query from the user
@@ -28,4 +28,4 @@ if openai_access_token:
     if query:
         # Search the web using the AI Assistant
         response = assistant.run(query, stream=False)
-        st.write(response)
+        st.write(response.content)

chat_with_X_tutorials/chat_with_research_papers/chat_arxiv_llama3.py

@@ -1,17 +1,17 @@
 # Import the required libraries
 import streamlit as st
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.llm.ollama import Ollama
+from agno.models.ollama import Ollama
-from phi.tools.arxiv_toolkit import ArxivToolkit
+from agno.tools.arxiv import ArxivTools
 
 # Set up the Streamlit app
 st.title("Chat with Research Papers 🔎🤖")
 st.caption("This app allows you to chat with arXiv research papers using Llama-3 running locally.")
 
 # Create an instance of the Assistant
-assistant = Assistant(
+assistant = Agent(
-llm=Ollama(
+model=Ollama(
-    model="llama3:instruct") , tools=[ArxivToolkit()], show_tool_calls=True
+    id="llama3.1:8b") , tools=[ArxivTools()], show_tool_calls=True
 )
 
 # Get the search query from the user
@@ -20,4 +20,4 @@ query= st.text_input("Enter the Search Query", type="default")
 if query:
     # Search the web using the AI Assistant
     response = assistant.run(query, stream=False)
-    st.write(response)
+    st.write(response.content)

chat_with_X_tutorials/chat_with_research_papers/requirements.txt

@@ -1,5 +1,5 @@
 streamlit 
-phidata
+agno
 arxiv
 openai
 pypdf

rag_tutorials/agentic_rag/rag_agent.py

@@ -1,9 +1,9 @@
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
-from phi.knowledge.pdf import PDFUrlKnowledgeBase
+from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
-from phi.vectordb.lancedb import LanceDb, SearchType
+from agno.vectordb.lancedb import LanceDb, SearchType
-from phi.playground import Playground, serve_playground_app
+from agno.playground import Playground, serve_playground_app
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
 
 db_uri = "tmp/lancedb"
 # Create a knowledge base from a PDF
@@ -19,7 +19,7 @@ rag_agent = Agent(
     model=OpenAIChat(id="gpt-4o"),
     agent_id="rag-agent",
     knowledge=knowledge_base, # Add the knowledge base to the agent
-    tools=[DuckDuckGo()],
+    tools=[DuckDuckGoTools()],
     show_tool_calls=True,
     markdown=True,
 )

rag_tutorials/agentic_rag/requirements.txt

@@ -1,4 +1,4 @@
-phidata
+agno
 openai
 lancedb 
 tantivy 

rag_tutorials/autonomous_rag/autorag.py

@@ -1,14 +1,14 @@
 import streamlit as st
 import nest_asyncio
 from io import BytesIO
-from phi.assistant import Assistant
+from agno.agent import Agent
-from phi.document.reader.pdf import PDFReader
+from agno.document.reader.pdf_reader import PDFReader
-from phi.llm.openai import OpenAIChat
+from agno.models.openai import OpenAIChat
-from phi.knowledge import AssistantKnowledge
+from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
-from phi.tools.duckduckgo import DuckDuckGo
+from agno.tools.duckduckgo import DuckDuckGoTools
-from phi.embedder.openai import OpenAIEmbedder
+from agno.embedder.openai import OpenAIEmbedder
-from phi.vectordb.pgvector import PgVector2
+from agno.vectordb.pgvector import PgVector, SearchType
-from phi.storage.assistant.postgres import PgAssistantStorage
+from agno.storage.agent.postgres import PostgresAgentStorage
 
 # Apply nest_asyncio to allow nested event loops, required for running async functions in Streamlit
 nest_asyncio.apply()
@@ -18,22 +18,22 @@ DB_URL = "postgresql+psycopg://ai:ai@localhost:5532/ai"
 
 # Function to set up the Assistant, utilizing caching for resource efficiency
 @st.cache_resource
-def setup_assistant(api_key: str) -> Assistant:
+def setup_assistant(api_key: str) -> Agent:
-    llm = OpenAIChat(model="gpt-4o-mini", api_key=api_key)
+    llm = OpenAIChat(id="gpt-4o-mini", api_key=api_key)
     # Set up the Assistant with storage, knowledge base, and tools
-    return Assistant(
+    return Agent(
-        name="auto_rag_assistant",  # Name of the Assistant
+        id="auto_rag_agent",  # Name of the Assistant
-        llm=llm,  # Language model to be used
+        model=llm,  # Language model to be used
-        storage=PgAssistantStorage(table_name="auto_rag_storage", db_url=DB_URL),  
+        storage=PostgresAgentStorage(table_name="auto_rag_storage", db_url=DB_URL),  
-        knowledge_base=AssistantKnowledge(
+        knowledge_base=PDFUrlKnowledgeBase(
-            vector_db=PgVector2(
+            vector_db=PgVector(
                 db_url=DB_URL,  
                 collection="auto_rag_docs",  
-                embedder=OpenAIEmbedder(model="text-embedding-ada-002", dimensions=1536, api_key=api_key),  
+                embedder=OpenAIEmbedder(id="text-embedding-ada-002", dimensions=1536, api_key=api_key),  
             ),
             num_documents=3,  
         ),
-        tools=[DuckDuckGo()],  # Additional tool for web search via DuckDuckGo
+        tools=[DuckDuckGoTools()],  # Additional tool for web search via DuckDuckGo
         instructions=[
             "Search your knowledge base first.",  
             "If not found, search the internet.",  
@@ -41,24 +41,23 @@ def setup_assistant(api_key: str) -> Assistant:
         ],
         show_tool_calls=True,  
         search_knowledge=True,  
-        read_chat_history=True,  
         markdown=True,  
         debug_mode=True,  
     )
 
 # Function to add a PDF document to the knowledge base
-def add_document(assistant: Assistant, file: BytesIO):
+def add_document(agent: Agent, file: BytesIO):
     reader = PDFReader()
     docs = reader.read(file)
     if docs:
-        assistant.knowledge_base.load_documents(docs, upsert=True)
+        agent.knowledge_base.load_documents(docs, upsert=True)
         st.success("Document added to the knowledge base.")
     else:
         st.error("Failed to read the document.")
 
 # Function to query the Assistant and return a response
-def query_assistant(assistant: Assistant, question: str) -> str:
+def query_assistant(agent: Agent, question: str) -> str:
-    return "".join([delta for delta in assistant.run(question)])
+    return "".join([delta for delta in agent.run(question)])
 
 # Main function to handle Streamlit app layout and interactions
 def main():
@@ -87,7 +86,7 @@ def main():
             with st.spinner("🤔 Thinking..."):
                 # Query the assistant and display the response
                 answer = query_assistant(assistant, question)
-                st.write("📝 **Response:**", answer)
+                st.write("📝 **Response:**", answer.content)
         else:
             # Show an error if the question input is empty
             st.error("Please enter a question.")

rag_tutorials/autonomous_rag/requirements.txt

@@ -1,5 +1,5 @@
 streamlit 
-phidata
+agno
 openai
 psycopg-binary
 pgvector

rag_tutorials/local_rag_agent/local_rag_agent.py

@@ -1,10 +1,10 @@
 # Import necessary libraries
-from phi.agent import Agent
+from agno.agent import Agent
-from phi.model.ollama import Ollama
+from agno.models.ollama import Ollama
-from phi.knowledge.pdf import PDFUrlKnowledgeBase
+from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
-from phi.vectordb.qdrant import Qdrant
+from agno.vectordb.qdrant import Qdrant
-from phi.embedder.ollama import OllamaEmbedder
+from agno.embedder.ollama import OllamaEmbedder
-from phi.playground import Playground, serve_playground_app
+from agno.playground import Playground, serve_playground_app
 
 # Define the collection name for the vector database
 collection_name = "thai-recipe-index"

rag_tutorials/local_rag_agent/requirements.txt

@@ -1,4 +1,4 @@
-phidata
+agno
 qdrant-client
 ollama
 pypdf 

rag_tutorials/rag_chain/app.py

@@ -10,8 +10,6 @@ from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.runnables import RunnablePassthrough
 
-from dotenv import load_dotenv
-load_dotenv()
 
 # Initialize embedding model
 embedding_model = GoogleGenerativeAIEmbeddings(model="models/embedding-001")