kausmeows

[
  {
    "content": "Je vais bien, merci ! Comment puis-je vous aider aujourd'hui ?",
    "content_type": "str",
    "metrics": {
      "input_tokens": 81,
      "output_tokens": 14,
      "total_tokens": 95,
      "prompt_tokens": 81,
      "completion_tokens": 14,

kausmeows

[
  {
    "content": "### Content Schedule for AI Trends in 2024\n\n**Week 1: Focus on Conversational AI and Model Evolutions**\n\n- **Post 1: Monday**\n  - **Topic**: The Future of Conversational AI in 2024\n  - **Content**: Overview of conversational AI growth, including market projections and potential sectors benefiting from advancements.\n  - **Research Source**: Forbes\n  - **Engagement**: Poll asking which industry will benefit the most from conversational AI.\n\n- **Post 2: Wednesday**\n  - **Topic**: Challenges of AI Model Evolution\n  - **Content**: Discuss the convergence in AI model development and the challenges in evaluating model intelligence. \n  - **Research Source**: MSN\n  - **Engagement**: Share an infographic explaining the evolution of AI models.\n\n- **Post 3: Friday**\n  - **Topic**: Introduction to AI Retrieval Models\n  - **Content**: Explain Gemini embeddings and their role in enhancing retrieval-augmented generation models.\n  - **Research Source**: Hackernews\n  - **Engagement**: 

kausmeows

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.storage.sqlite import SqliteStorage
from agno.team import Team
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.hackernews import HackerNewsTools
from agno.workflow.v2.step import Step, StepInput, StepOutput
from agno.workflow.v2.workflow import Workflow

# Define agents

kausmeows

"""Please install dependencies using:
pip install openai newspaper4k lxml_html_clean agno
"""

import json
from typing import Iterator

import httpx
from agno.agent import Agent, RunResponse
from agno.tools.newspaper4k import Newspaper4kTools

kausmeows

from agno.agent import Agent
from agno.knowledge.text import TextKnowledgeBase
from agno.utils.media import (
    SampleDataFileExtension,
    download_knowledge_filters_sample_data,
)
from agno.vectordb.lancedb import LanceDb


def initialize_vector_db(table_name="recipes", uri="tmp/lancedb"):

kausmeows

"""Run `pip install duckduckgo-search` to install dependencies."""

from agno.agent import Agent
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.models.litellm import LiteLLM

# Make sure the model used supports functional tool calling like openai, better llama models, etc
agent = Agent(
    model=LiteLLM(id="openrouter/meta-llama/llama-4-maverick"),
    tools=[DuckDuckGoTools()],

kausmeows

# %% [markdown]
# # Documentation for Current Notebook
# This notebook is designed to demonstrate the creation and usage of an SEO Agent for optimizing web content. The agent leverages various tools and APIs, such as SERP API, Google Search Tools, ExaTools, to enhance content visibility on search engines.
#
# ## Key Components:
# 1. **SERP API Tool**: Fetches search engine results and extracts trending keywords.
# 2. **SEO Agent**: A custom agent built using the `agno` library to process and optimize content based on SEO best practices.
# 3. **Environment Variables**: Uses `.env` file to securely store API keys.
# 4. **Input and Output**: Accepts JSON input containing HTML tags and content, processes it, and returns optimized content in JSON format.
#