admin-valentin/awesome-llm-apps
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

phidata -> agno

Browse source
This commit is contained in:
Madhu 2025-02-02 19:32:29 +05:30
parent 5bd5227288
commit df784d9c00
3 changed files with 15 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
ai_agent_tutorials/ai_system_architect_r1/README.md
View file

@ -1,6 +1,6 @@
# 🤖 AI System Architect Advisor with R1 # 🤖 AI System Architect Advisor with R1
A Streamlit application that provides expert software architecture analysis and recommendations using a dual-model approach combining DeepSeek R1's Reasoning and Claude. The system provides detailed technical analysis, implementation roadmaps, and architectural decisions for complex software systems. An Agno agentic system that provides expert software architecture analysis and recommendations using a dual-model approach combining DeepSeek R1's Reasoning and Claude. The system provides detailed technical analysis, implementation roadmaps, and architectural decisions for complex software systems.
## Features ## Features

18
ai_agent_tutorials/ai_system_architect_r1/ai_system_architect_r1.py
View file

@ -8,8 +8,8 @@ from dotenv import load_dotenv
from pydantic import BaseModel, Field from pydantic import BaseModel, Field
from enum import Enum from enum import Enum
import json import json
from phi.agent import Agent, RunResponse from agno.agent import Agent, RunResponse
from phi.model.anthropic import Claude from agno.models.anthropic import Claude
# Model Constants # Model Constants
DEEPSEEK_MODEL: str = "deepseek-reasoner" DEEPSEEK_MODEL: str = "deepseek-reasoner"
@ -74,14 +74,22 @@ class ModelChain:
base_url="https://api.deepseek.com" base_url="https://api.deepseek.com"
) )
self.claude_client = anthropic.Anthropic(api_key=anthropic_api_key) self.claude_client = anthropic.Anthropic(api_key=anthropic_api_key)
self.agent = Agent(
model=Claude(id="claude-3-5-sonnet-20241022", api_key=anthropic_api_key), # Create Claude model with system prompt
claude_model = Claude(
id="claude-3-5-sonnet-20241022",
api_key=anthropic_api_key,
system_prompt="""Given the user's query and the DeepSeek reasoning: system_prompt="""Given the user's query and the DeepSeek reasoning:
1. Provide a detailed analysis of the architecture decisions 1. Provide a detailed analysis of the architecture decisions
2. Generate a project implementation roadmap 2. Generate a project implementation roadmap
3. Create a comprehensive technical specification document 3. Create a comprehensive technical specification document
4. Format the output in clean markdown with proper sections 4. Format the output in clean markdown with proper sections
5. Include diagrams descriptions in mermaid.js format""", 5. Include diagrams descriptions in mermaid.js format"""
)
# Initialize agent with configured model
self.agent = Agent(
model=claude_model,
markdown=True markdown=True
) )

2
ai_agent_tutorials/ai_system_architect_r1/requirements.txt
View file

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