___init__

README.md

@@ -50,7 +50,7 @@ model = OpenAIChat(
 )
 
 # Initialize the agent
-agent = Agent(
+base_agent = Agent(
  agent_name="News-Agent-V1",
  # system_prompt=FINANCIAL_AGENT_SYS_PROMPT,
  llm=model,
@@ -70,7 +70,7 @@ agent = Agent(
 # Agent
 agent = NewsAgent(
  agent_name="news-agent-v1",
- agent=agent,
+ agent=base_agent,
  newsapi_api_key=os.getenv("NEWSAPI_API_KEY"),
  system_prompt=None,
  return_json=True,
@@ -80,8 +80,8 @@ agent = NewsAgent(
 
 
 # Run the agent
-# agent.run(["multi-agent collaboration"])
-agent.run_concurrently(["Swarm Multi-Agent", "AGI"])
+print(agent.run("multi-agent collaboration"))
+print(agent.run_concurrently(["OpenAI", "Anthropic"]))
 
 
 ```

example.py

@@ -47,5 +47,6 @@
 
 
 # Run the agent
-print(agent.run("multi-agent collaboration"))
+# print(agent.run("multi-agent collaboration"))
 print(agent.run_concurrently(["OpenAI", "Anthropic"]))
+# print(agent.return_sources("Science"))

news_swarm/__init__.py

@@ -0,0 +1,15 @@
+from news_swarm.main import NewsAgent
+from news_swarm.tool import (
+ fetch_stock_news,
+ return_headlines,
+ return_sources,
+)
+from news_swarm.prompts import NEWS_SYS_PROMPT
+
+__all__ = [
+ "NewsAgent",
+ "fetch_stock_news",
+ "return_headlines",
+ "return_sources",
+ "NEWS_SYS_PROMPT",
+]

news_swarm/main.py

@@ -7,9 +7,10 @@
 from pydantic import BaseModel, Field
 from swarms import Agent, create_file_in_folder
 
-from news_swarm.tool import fetch_stock_news
+from news_swarm.tool import fetch_stock_news, return_sources
 from loguru import logger
 
+
 class InputLog(BaseModel):
  id: Optional[str] = Field(
  default=str(uuid.uuid4()),
@@ -66,6 +67,17 @@ class NewsAgent(Agent):
  """
  A specialized agent for fetching and processing news articles based on given tasks.
  It utilizes the News API to fetch articles and a language model to generate summaries.
+
+ Args:
+ agent_name (str): The name of the agent.
+ newsapi_api_key (str, optional): The API key for News API. Defaults to None.
+ system_prompt (str, optional): The system prompt for the language model. Defaults to None.
+ llm (BaseLLM, optional): The language model to use for summarization. Defaults to None.
+ agent (Agent, optional): The base agent to inherit from. Defaults to None.
+ start_date (Optional[str], optional): The start date for the news query in 'YYYY-MM-DD' format. Defaults to None.
+ end_date (Optional[str], optional): The end date for the news query in 'YYYY-MM-DD' format. Defaults to None.
+ return_json (bool, optional): If True, return the result as a JSON object, otherwise return a formatted string. Defaults to False.
+ max_articles (int, optional): The maximum number of articles to fetch. Defaults to 5.
  """
 
  def __init__(
@@ -80,20 +92,7 @@ def __init__(
  max_articles: int = 5,
  autosave: bool = True,
  ):
- """
- Initializes the NewsAgent with the necessary parameters.
 
- Args:
- agent_name (str): The name of the agent.
- newsapi_api_key (str, optional): The API key for News API. Defaults to None.
- system_prompt (str, optional): The system prompt for the language model. Defaults to None.
- llm (BaseLLM, optional): The language model to use for summarization. Defaults to None.
- agent (Agent, optional): The base agent to inherit from. Defaults to None.
- start_date (Optional[str], optional): The start date for the news query in 'YYYY-MM-DD' format. Defaults to None.
- end_date (Optional[str], optional): The end date for the news query in 'YYYY-MM-DD' format. Defaults to None.
- return_json (bool, optional): If True, return the result as a JSON object, otherwise return a formatted string. Defaults to False.
- max_articles (int, optional): The maximum number of articles to fetch. Defaults to 5.
- """
  self.agent_name = agent_name
  self.system_prompt = system_prompt
  self.newsapi_api_key = newsapi_api_key
@@ -120,15 +119,17 @@ def __init__(
 
  def run(self, task: str, *args, **kwargs):
  """
- Runs the news fetching and summarization process sequentially for each task.
+ Executes the news retrieval and summarization process sequentially for a given task.
+
+ This method fetches news articles related to the specified task, summarizes the content, and logs the process. It supports both string and JSON output formats based on the `return_json` parameter.
 
  Args:
- tasks (List[str]): A list of tasks or queries to process.
+ task (str): The task or query to process.
 
  Returns:
- Union[str, dict]: The output of the process, either a formatted string or a JSON object depending on the return_json parameter.
+ Union[str, dict]: The output of the process, either a formatted string or a JSON object depending on the `return_json` parameter.
  """
- logger.info("Running task Now")
+ logger.info("Initiating task execution")
  self.output_log.input_log.query = task
 
  string_query, *data_dict = fetch_stock_news(
@@ -138,8 +139,8 @@ def run(self, task: str, *args, **kwargs):
  self.end_date,
  max_articles=self.max_articles,
  )
- 
- logger.info(f"Fetched the articles now")
+
+ logger.info(f"Completed fetching articles for task {task}")
 
  summary = self.agent.run(string_query)
 
@@ -149,29 +150,19 @@ def run(self, task: str, *args, **kwargs):
  )
 
  self.output_log.output_logs.append(output_log_indi)
-
- logger.info(f"Finished summarizing this query {task}")
 
- # # Save the log
- # create_file_in_folder(
- # "news_agent_runs",
- # f"news_agent_run_id:{self.output_log.id}.json",
- # self.output_log.model_dump_json(indent=4),
- # )
+ logger.info(f"Summarization completed for task {task}")
 
- # if self.return_json is True:
- # return self.output_log.model_dump_json(indent=4)
-
- # else:
- # return summary
  return summary
 
  def run_concurrently(self, tasks: List[str]) -> str:
  """
- Runs the news fetching and summarization process concurrently for each task.
+ Executes the news retrieval and summarization process concurrently for a list of tasks.
+
+ This method leverages multithreading to process multiple tasks simultaneously, ensuring efficient handling of multiple queries. The output is always in JSON format.
 
  Args:
- tasks (List[str]): A list of tasks or queries to process.
+ tasks (List[str]): A list of tasks or queries to process concurrently.
 
  Returns:
  str: The output of the process as a JSON object.
@@ -183,8 +174,7 @@ def run_concurrently(self, tasks: List[str]) -> str:
  }
  for future in futures:
  future.result() # Wait for all tasks to complete
-
-
+
  # Save the log
  create_file_in_folder(
  "news_agent_runs",
@@ -193,3 +183,17 @@ def run_concurrently(self, tasks: List[str]) -> str:
  )
 
  return self.output_log.model_dump_json(indent=4)
+
+ def return_sources(self, source: Any, *args, **kwargs):
+ """
+ Returns sources related to a given source or query.
+
+ This method is a wrapper for fetching sources based on a provided source or query. It utilizes the `newsapi_api_key` for authentication.
+
+ Args:
+ source (Any): The source or query to fetch related sources for.
+
+ Returns:
+ Any: The fetched sources based on the provided source or query.
+ """
+ return return_sources(source, self.newsapi_api_key)

news_swarm/tool.py

@@ -1,5 +1,5 @@
 from newsapi import NewsApiClient
-from typing import Optional, Dict, Union, List
+from typing import Optional, Dict, Union, List, Literal
 
 
 def fetch_stock_news(
@@ -103,3 +103,60 @@ def process_article(article: Dict[str, str]) -> Dict[str, str]:
 
 # # Example
 # out = fetch_stock_news("Swarms")
+
+
+def return_sources(
+ source: Literal[
+ "business",
+ "entertainment",
+ "general",
+ "health",
+ "science",
+ "sports",
+ "technology",
+ ],
+ newsapi_api_key: str = None,
+ *args,
+ **kwargs,
+):
+ """
+ Fetches stock news for a query within a specified date range using NewsApiClient.
+
+ Args:
+ query (str): The query name or stock symbol to query news for.
+ newsapi_api_key (str): Your API key for News API.
+ start_date (Optional[str]): The start date for the news query in 'YYYY-MM-DD' format (default: None).
+ end_date (Optional[str]): The end date for the news query in 'YYYY-MM-DD' format (default: None).
+ max_articles (int): The maximum number of articles to retrieve (default: 5).
+ return_json (bool): If True, return the result as a JSON object, otherwise return a formatted string (default: False).
+
+ Returns:
+ Union[Dict[str, Union[str, List[Dict[str, str]]]], str]:
+ A JSON object (if return_json=True) containing articles and metadata, or a formatted string of the news articles.
+ """
+
+ # Initialize the NewsApiClient with the provided API key
+ newsapi = NewsApiClient(api_key=newsapi_api_key)
+
+ data = newsapi.get_sources(category=source, *args, **kwargs)
+
+ return data
+
+
+def return_headlines(
+ source: str = None, newsapi_api_key: str = None, *args, **kwargs
+):
+ """
+ Fetches stock news for a query within a specified date range using NewsApiClient.
+
+ Args:
+ query (str): The query name or stock symbol to query news for.
+ newsapi_api_key (str): Your API key for News API.
+ """
+
+ # Initialize the NewsApiClient with the provided API key
+ newsapi = NewsApiClient(api_key=newsapi_api_key)
+
+ data = newsapi.get_top_headlines(sources=source, *args, **kwargs)
+
+ return data

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "news-swarm"
-version = "0.0.5"
+version = "0.0.6"
 description = "NewsAgent - TGSC"
 license = "MIT"
 authors = ["Kye Gomez <kye@apac.ai>"]