Upload 5 files

crewai/tools/browser_tools.py

@@ -0,0 +1,38 @@
+import json
+import os
+
+import requests
+from crewai import Agent, Task
+from langchain.tools import tool
+from unstructured.partition.html import partition_html
+
+
+class BrowserTools():
+
+  @tool("Scrape website content")
+  def scrape_and_summarize_website(website):
+    """Useful to scrape and summarize a website content"""
+    url = f"https://chrome.browserless.io/content?token={os.environ['BROWSERLESS_API_KEY']}"
+    payload = json.dumps({"url": website})
+    headers = {'cache-control': 'no-cache', 'content-type': 'application/json'}
+    response = requests.request("POST", url, headers=headers, data=payload)
+    elements = partition_html(text=response.text)
+    content = "\n\n".join([str(el) for el in elements])
+    content = [content[i:i + 8000] for i in range(0, len(content), 8000)]
+    summaries = []
+    for chunk in content:
+      agent = Agent(
+          role='Principal Researcher',
+          goal=
+          'Do amazing research and summaries based on the content you are working with',
+          backstory=
+          "You're a Principal Researcher at a big company and you need to do research about a given topic.",
+          allow_delegation=False)
+      task = Task(
+          agent=agent,
+          description=
+          f'Analyze and summarize the content below, make sure to include the most relevant information in the summary, return only the summary nothing else.\n\nCONTENT\n----------\n{chunk}'
+      )
+      summary = task.execute()
+      summaries.append(summary)
+    return "\n\n".join(summaries)

crewai/tools/calculator_tools.py

@@ -0,0 +1,13 @@
+from langchain.tools import tool
+
+
+class CalculatorTools():
+
+  @tool("Make a calcualtion")
+  def calculate(operation):
+    """Useful to perform any mathematica calculations, 
+    like sum, minus, mutiplcation, division, etc.
+    The input to this tool should be a mathematical 
+    expression, a couple examples are `200*7` or `5000/2*10`
+    """
+    return eval(operation)

crewai/tools/search_tools.py

@@ -0,0 +1,57 @@
+import json
+import os
+
+import requests
+from langchain.tools import tool
+
+
+class SearchTools():
+  @tool("Search the internet")
+  def search_internet(query):
+    """Useful to search the internet 
+    about a a given topic and return relevant results"""
+    top_result_to_return = 4
+    url = "https://google.serper.dev/search"
+    payload = json.dumps({"q": query})
+    headers = {
+        'X-API-KEY': os.environ['SERPER_API_KEY'],
+        'content-type': 'application/json'
+    }
+    response = requests.request("POST", url, headers=headers, data=payload)
+    results = response.json()['organic']
+    string = []
+    for result in results[:top_result_to_return]:
+      try:
+        string.append('\n'.join([
+            f"Title: {result['title']}", f"Link: {result['link']}",
+            f"Snippet: {result['snippet']}", "\n-----------------"
+        ]))
+      except KeyError:
+        next
+
+    return '\n'.join(string)
+
+  @tool("Search news on the internet")
+  def search_news(query):
+    """Useful to search news about a company, stock or any other
+    topic and return relevant results"""""
+    top_result_to_return = 4
+    url = "https://google.serper.dev/news"
+    payload = json.dumps({"q": query})
+    headers = {
+        'X-API-KEY': os.environ['SERPER_API_KEY'],
+        'content-type': 'application/json'
+    }
+    response = requests.request("POST", url, headers=headers, data=payload)
+    results = response.json()['news']
+    string = []
+    for result in results[:top_result_to_return]:
+      try:
+        string.append('\n'.join([
+            f"Title: {result['title']}", f"Link: {result['link']}",
+            f"Snippet: {result['snippet']}", "\n-----------------"
+        ]))
+      except KeyError:
+        next
+
+    return '\n'.join(string)

crewai/tools/sec_tools.py

@@ -0,0 +1,108 @@
+import os
+
+import requests
+
+from langchain.tools import tool
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+
+from sec_api import QueryApi
+from unstructured.partition.html import partition_html
+
+class SECTools():
+  @tool("Search 10-Q form")
+  def search_10q(data):
+    """
+    Useful to search information from the latest 10-Q form for a
+    given stock.
+    The input to this tool should be a pipe (|) separated text of 
+    length two, representing the stock ticker you are interested, what
+    question you have from it.
+		For example, `AAPL|what was last quarter's revenue`.
+    """
+    stock, ask = data.split("|")
+    queryApi = QueryApi(api_key=os.environ['SEC_API_API_KEY'])
+    query = {
+      "query": { 
+        "query_string": {
+          "query": f"ticker:{stock} AND formType:\"10-Q\""
+        } 
+      },
+      "from": "0",
+      "size": "1",
+      "sort": [{ "filedAt": { "order": "desc" }}]
+    }
+
+    filings = queryApi.get_filings(query)['filings']
+    link = filings[0]['linkToFilingDetails']    
+    answer = SECTools.__embedding_search(link, ask)
+    return answer
+
+  @tool("Search 10-K form")
+  def search_10k(data):
+    """
+    Useful to search information from the latest 10-K form for a
+    given stock.
+    The input to this tool should be a pipe (|) separated text of 
+    length two, representing the stock ticker you are interested, what
+    question you have from it.
+    For example, `AAPL|what was last year's revenue`.
+    """
+    stock, ask = data.split("|")
+    queryApi = QueryApi(api_key=os.environ['SEC_API_API_KEY'])
+    query = {
+      "query": { 
+        "query_string": {
+          "query": f"ticker:{stock} AND formType:\"10-K\""
+        } 
+      },
+      "from": "0",
+      "size": "1",
+      "sort": [{ "filedAt": { "order": "desc" }}]
+    }
+
+    filings = queryApi.get_filings(query)['filings']
+    link = filings[0]['linkToFilingDetails']
+    answer = SECTools.__embedding_search(link, ask)
+    return answer
+  
+  def __embedding_search(url, ask):
+    text = SECTools.__download_form_html(url)
+    elements = partition_html(text=text)
+    content = "\n".join([str(el) for el in elements])
+    text_splitter = CharacterTextSplitter(
+        separator = "\n",
+        chunk_size = 1000,
+        chunk_overlap  = 150,
+        length_function = len,
+        is_separator_regex = False,
+    )
+    docs = text_splitter.create_documents([content])
+    retriever = FAISS.from_documents(
+      docs, OpenAIEmbeddings()
+    ).as_retriever()
+    answers = retriever.get_relevant_documents(ask, top_k=4)
+    answers = "\n\n".join([a.page_content for a in answers])
+    return answers
+
+  def __download_form_html(url):    
+    headers = {
+      'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+      'Accept-Encoding': 'gzip, deflate, br',
+      'Accept-Language': 'en-US,en;q=0.9,pt-BR;q=0.8,pt;q=0.7',
+      'Cache-Control': 'max-age=0',
+      'Dnt': '1',
+      'Sec-Ch-Ua': '"Not_A Brand";v="8", "Chromium";v="120"',
+      'Sec-Ch-Ua-Mobile': '?0',
+      'Sec-Ch-Ua-Platform': '"macOS"',
+      'Sec-Fetch-Dest': 'document',
+      'Sec-Fetch-Mode': 'navigate',
+      'Sec-Fetch-Site': 'none',
+      'Sec-Fetch-User': '?1',
+      'Upgrade-Insecure-Requests': '1',
+      'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+    }
+
+    response = requests.get(url, headers=headers)
+    return response.text