Agentverse: allowed imports

Introduction

In the Agentverse (opens in a new tab) code editor, you have the freedom to import and utilize a selected set of modules to create your code, while maintaining security and control. These pre-approved modules offer a diverse range of functionalities, allowing you to build complex agents.

The Agentverse now provides full Python support! This means that all Hosted Agents will now support the full Python built-in library plus the following packages:

Allowed imports

uagents

Build fast and lightweight for decentralized scenarios using the uagents Framework. Checkout the documentation and the uagents package (opens in a new tab) for more information.

Available classes: Model, Context, Protocol.

Example:


from uagents import Context, Model
 
class Message(Model):
    text: str
 
@agent.on_interval(period=2.0)
async def print_message(ctx: Context):
    msg = Message(text=f"Hello there my wallet address is {ctx.wallet}.")
    print(msg.text)

requests

This package allows you to interact with HTTP requests and responses.

Available functions: get, post, put, patch, delete.

Example:


import requests
 
response = requests.get('https://api.github.com')
if response.status_code == 200:
    print('Success!')
elif response.status_code == 404:
    print('Not Found.')
 
print(response.headers)

cosmpy

A Python library for interacting with Cosmos-based blockchains. Checkout the CosmPy documentation and the CosmPy package (opens in a new tab)for more information.

Full access to all functions and features.

Example:


from cosmpy import aerial
 
# Define network configuration, faucet and ledger
network = aerial.client.NetworkConfig.fetchai_stable_testnet()
faucet_api = aerial.faucet.FaucetApi(network)
ledger = aerial.client.LedgerClient(network)
 
MINIMUM_BALANCE = 100000000000000000
 
@agent.on_interval(period=20.0)
async def get_tokens(ctx: Context):
 
    agent_balance = ledger.query_bank_balance(ctx.wallet)
 
    if agent_balance < MINIMUM_BALANCE:
        print("Providing wealth to agent...")
        faucet_api.get_wealth(ctx.wallet)

pydantic

A package to ensure data validation and settings management. It simplifies the process of defining and validating data models by providing a way to declare and enforce data types, constraints, and validation rules on Python data structures.

Full access to all functions and features.

Example:


from pydantic import BaseModel
 
data = {
    "name": "alice",
    "age": 21
}
 
class User(BaseModel):
    name: str
    age: int
 
user = User(**data)
 
print(user)

ai_engine

Integrate Agents with the AI Engine to perform a wide variety tasks, including in booking services, make reservations, and provide answers to different queries. Checkout the AI Engine documentation and the AI Engine package (opens in a new tab) for further information.

Full access to all functions and features.

Example:


from uagents import Context, Model, Protocol
from ai_engine import UAgentResponse, UAgentResponseType
 
simples = Protocol(name="simples", version="v1.1")
 
class Request(Model):
    message: str
 
@simples.on_message(model=Request, replies={UAgentResponse})
async def handle_message(ctx: Context, sender: str, msg: Request):
    await ctx.send(sender, UAgentResponse(message="0", type=UAgentResponseType.FINAL))

MySQLdb

MySQLdb is a Python library for accessing MySQL databases. It provides a Python interface to MySQL, allowing you to interact with MySQL databases from within your Python code.

Full access to all functions and features.

Example:


import MySQLdb
 
# Connect to the MySQL database
connection = MySQLdb.connect(host='localhost', user='username', passwd='password', db='database_name')
 
try:
  # Create a cursor object to execute SQL queries
  cursor = connection.cursor()
 
  # Example query: Select all rows from a table
  cursor.execute("SELECT * FROM your_table")
 
  # Print the fetched rows
  for row in cursor.fetchall():
      print(row)
 
finally:
  # Close the cursor and connection
  cursor.close()
  connection.close()

pymongo

pymongo allows Python applications to interact with MongoDB databases, making it easy to perform various database operations such as inserting, updating, deleting, and querying documents.

Full access to all functions and features.

Example:


from pymongo import MongoClient
 
# Connect to MongoDB server
client = MongoClient('mongodb://localhost:27017/')
 
# Access a specific database
db = client['my_database']
 
# Access a specific collection within the database
collection = db['my_collection']
 
# Insert a document into the collection
document = {'name': 'John', 'age': 30, 'city': 'New York'}
collection.insert_one(document)
 
# Query documents from the collection
query = {'city': 'New York'}
result = collection.find(query)
 
# Print the documents returned by the query
for doc in result:
  print(doc)
 
# Close the connection to MongoDB
client.close()

bs4 (BeautifulSoup)

bs4 make it easy to parse and interact with HTML and XML documents for web scraping or data extraction.

Example:


from bs4 import BeautifulSoup
import requests
 
# Fetch the content of a webpage
response = requests.get("https://example.com")
 
# Parse the HTML content
soup = BeautifulSoup(response.content, "html.parser")
 
# Extract and print the page title
print(soup.title.string)

faiss-cpu

faiss-cpu allow you to efficiently perform nearest neighbor search on high-dimensional dense vectors. It is used in machine learning for clustering and similarity search.

Example:


import faiss
import numpy as np
 
# Create a dataset of 128-dimensional vectors
data = np.random.random((100, 128)).astype('float32')
 
# Create an index using L2 (Euclidean) distance
index = faiss.IndexFlatL2(128)
 
# Add vectors to the index
index.add(data)
 
# Perform a search to find the 5 nearest neighbors
query = np.random.random((1, 128)).astype('float32')
distances, indices = index.search(query, k=5)
print(indices)

fetchai-babble

fetchai-babble allows you to interact with the Fetch.ai messaging service (called Memorandum). Further reference here (opens in a new tab).

Example:


from babble import Client, Identity
 
# create a set of agents with random identities
client1 = Client('agent1.....', Identity.generate())
client2 = Client('agent1.....', Identity.generate())
 
# send a message from one client to another
client1.send(client2.delegate_address, "why hello there")
 
# receive the messages from the other client
for msg in client2.receive():
    print(msg.text)

google-generativeai

google-generativeai allows you to build with the Gemini API. The Gemini API gives you access to Gemini models created by Google DeepMind. Gemini models are built from the ground up to be multimodal, so you can reason seamlessly across text, images, and code. Further reference here (opens in a new tab).

Example:


import google.generativeai as genai
import os
 
genai.configure(api_key=os.environ["GEMINI_API_KEY"])
 
model = genai.GenerativeModel('gemini-1.5-flash')
response = model.generate_content("The opposite of hot is")
print(response.text)

langchain-anthropic

langchain-anthropic contains the LangChain integration for Anthropic's generative models. Further reference here (opens in a new tab).

Example:


from langchain_anthropic import ChatAnthropic
from langchain_core.messages import AIMessage, HumanMessage
 
model = ChatAnthropic(model="claude-3-opus-20240229", temperature=0, max_tokens=1024)
 
message = HumanMessage(content="What is the capital of France?")
 
response = model.invoke([message])

langchain-community

langchain-community contains third-party integrations that implement the base interfaces defined in LangChain Core, making them ready-to-use in any LangChain application. It is automatically installed by langchain, but can also be used separately. Further reference here (opens in a new tab).

Example:


import bs4
from langchain_community.document_loaders import WebBaseLoader
 
# Only keep post title, headers, and content from the full HTML.
bs4_strainer = bs4.SoupStrainer(class_=("post-title", "post-header", "post-content"))
loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs={"parse_only": bs4_strainer},
)
docs = loader.load()
 
len(docs[0].page_content)

langchain-core

langchain-core contains the base abstractions that power the rest of the LangChain ecosystem. Further reference here (opens in a new tab).

Example:


from langchain_core.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
 
llm = ChatGoogleGenerativeAI(model="gemini-pro-vision")
# example
message = HumanMessage(
    content=[
        {
            "type": "text",
            "text": "What's in this image?",
        },  # You can optionally provide text parts
        {"type": "image_url", "image_url": "https://picsum.photos/seed/picsum/200/300"},
    ]
)
llm.invoke([message])

langchain-google-genai

langchain-google-genai contains the LangChain integrations for Gemini through their generative-ai SDK. Further reference here (opens in a new tab).

Example:


from langchain_core.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
 
llm = ChatGoogleGenerativeAI(model="gemini-pro-vision")
# example
message = HumanMessage(
    content=[
        {
            "type": "text",
            "text": "What's in this image?",
        },  # You can optionally provide text parts
        {"type": "image_url", "image_url": "https://picsum.photos/seed/picsum/200/300"},
    ]
)
llm.invoke([message])

langchain-google-vertexai

langchain-google-vertexai contains the LangChain integrations for Google Cloud generative models. Further reference here (opens in a new tab).

Example:


from langchain_core.messages import HumanMessage
from langchain_google_vertexai import ChatVertexAI
 
llm = ChatVertexAI(model_name="gemini-pro-vision")
# example
message = HumanMessage(
    content=[
        {
            "type": "text",
            "text": "What's in this image?",
        },  # You can optionally provide text parts
        {"type": "image_url", "image_url": {"url": "https://picsum.photos/seed/picsum/200/300"}},
    ]
)
llm.invoke([message])

langchain-openai

langchain-openai contains the LangChain integrations for OpenAI through their openai SDK. Further reference here (opens in a new tab).

Example:


from langchain_openai import ChatOpenAI
 
llm = ChatOpenAI(
    model="gpt-4o",
    temperature=0,
    max_tokens=None,
    timeout=None,
    max_retries=2,
    # api_key="...",  # if you prefer to pass api key in directly instaed of using env vars
    # base_url="...",
    # organization="...",
    # other params...
)

langchain-text-splitters

langchain-text-splitters contains utilities for splitting into chunks a wide variety of text documents. Further reference here (opens in a new tab).

Example:


from langchain_text_splitters import RecursiveCharacterTextSplitter
 
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000, chunk_overlap=200, add_start_index=True
)
all_splits = text_splitter.split_documents(docs)
 
len(all_splits)

langchain

langchain assists in the development of applications integrating with LLMs. Further reference here (opens in a new tab).

Example:


import bs4
from langchain import hub
from langchain_chroma import Chroma
from langchain_community.document_loaders import WebBaseLoader
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
 
# Load, chunk and index the contents of the blog.
loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(
            class_=("post-content", "post-title", "post-header")
        )
    ),
)
docs = loader.load()
 
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
splits = text_splitter.split_documents(docs)
vectorstore = Chroma.from_documents(documents=splits, embedding=OpenAIEmbeddings())
 
# Retrieve and generate using the relevant snippets of the blog.
retriever = vectorstore.as_retriever()
prompt = hub.pull("rlm/rag-prompt")
 
def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)
 
rag_chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)
 
rag_chain.invoke("What is Task Decomposition?")

nltk

nltk is a package for natural language processing.

Example:


import nltk
nltk.download('punkt')
 
from nltk.tokenize import word_tokenize
 
text = "This is an example sentence, showing off the tokenization process."
 
tokens = word_tokenize(text)
 
print(tokens)
 
# ['This', 'is', 'an', 'example', 'sentence', ',', 'showing', 'off', 'the', 'tokenization', 'process', '.']

openai

openai provides easy access to the OpenAI REST API. The library includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients powered by httpx.

Example:


import os
from openai import OpenAI
 
client = OpenAI(
    # This is the default and can be omitted
    api_key=os.environ.get("OPENAI_API_KEY"),
)
 
chat_completion = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "Say this is a test",
        }
    ],
    model="gpt-3.5-turbo",
)

tenacity

tenacity is a general-purpose retrying library to simplify the task of adding retry behavior to just about anything.

Example:


import random
from tenacity import retry
 
@retry
def do_something_unreliable():
    if random.randint(0, 10) > 1:
        raise IOError("Broken sauce, everything is hosed!!!111one")
    else:
        return "Awesome sauce!"
 
print(do_something_unreliable())

unstructured

unstructured is a library for processing and extracting data from unstructured file formats such as PDFs, Word documents, and more.

Example:


from unstructured.partition.auto import partition
 
elements = partition(filename="example-docs/fake-email.eml")
print("\n\n".join([str(el) for el in elements]))

validators

validators is a Python library designed for data validation. It provides simple functions to verify the validity of various types of data. Further reference here (opens in a new tab).

Example:


import validators
print(validators.email('[email protected]'))  # True
print(validators.email('invalid-email'))  # ValidationFailure

Multi-file Support

The Agentverse Code Editor enhances your agent development experience with multi-file support, enabling you to tackle complex projects with ease. Leverage this feature to:

Interact between files: simply import functions, classes, and variables from one file to another.
Modular development: divide your projects into manageable components for streamlined creation.
Code reuse: utilize modules across various sections of your project for efficient development.
Enhanced organization: maintain a structured and organized codebase for easier maintenance.

If you want to create new files you just need to click on + New File on Agentverse (opens in a new tab) inside your managed agent.

You can create a Python message file with the following Model class:


from uagents import Model
 
class Sentence(Model):
    text: str

Then, you can just import the Sentence data model to your agent.py file and make use of it:


from uagents import Context
from message import Sentence
 
@agent.on_interval(period=2.0)
async def print_message(ctx: Context):
    msg = Sentence(text=f"Hello there my wallet address is {ctx.wallet}.")
    print(msg.text)

For additional information on Functions, head over to Agent Functions and Register Agent Functions resources.

Was this page helpful?

You can also leave detailed feedbackon Github

Agentverse: Dice Roll agent Agentverse Teams