llama-index-tools-praisonai
LlamaIndex tool integration for PraisonAI multi-agent framework.
Installation
pip install llama-index-tools-praisonai
Prerequisites
- Install and start PraisonAI server:
pip install praisonai
praisonai serve agents.yaml --port 8080
Usage
Basic Usage with LlamaIndex Agent
from llama_index_tools_praisonai import PraisonAIToolSpec
from llama_index.agent.openai import OpenAIAgent
# Create the PraisonAI tool spec
spec = PraisonAIToolSpec(api_url="http://localhost:8080")
tools = spec.to_tool_list()
# Create agent with PraisonAI tools
agent = OpenAIAgent.from_tools(tools, verbose=True)
# Use the agent
response = agent.chat("Research the latest trends in AI and summarize them")
print(response)
Using Individual Tools
from llama_index_tools_praisonai import PraisonAIToolSpec
spec = PraisonAIToolSpec()
# Run a specific agent
result = spec.run_agent(query="Research quantum computing", agent="researcher")
print(result)
# Run the full workflow
result = spec.run_workflow(query="Create a blog post about AI")
print(result)
# List available agents
agents = spec.list_agents()
print(agents)
Async Usage
import asyncio
from llama_index_tools_praisonai import PraisonAIToolSpec
async def main():
spec = PraisonAIToolSpec()
# Async agent execution
result = await spec.arun_agent(query="Research AI", agent="researcher")
print(result)
# Async workflow execution
result = await spec.arun_workflow(query="Create content")
print(result)
asyncio.run(main())
With ReAct Agent
from llama_index_tools_praisonai import PraisonAIToolSpec
from llama_index.core.agent import ReActAgent
from llama_index.llms.openai import OpenAI
spec = PraisonAIToolSpec()
tools = spec.to_tool_list()
llm = OpenAI(model="gpt-4o-mini")
agent = ReActAgent.from_tools(tools, llm=llm, verbose=True)
response = agent.chat("Use PraisonAI to research and write about machine learning")
print(response)
Configuration
| Parameter | Default | Description |
|---|---|---|
api_url |
http://localhost:8080 |
PraisonAI server URL |
timeout |
300 |
Request timeout in seconds |
Available Tools
| Tool | Description |
|---|---|
run_agent |
Run a specific PraisonAI agent (e.g., researcher, writer) |
run_workflow |
Run the full multi-agent workflow |
list_agents |
List all available agents |
Links
License
MIT
Metadata
Release files for llama-index-tools-praisonai 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| llama_index_tools_praisonai-0.1.0.tar.gz | 5.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| llama_index_tools_praisonai-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 11.1 kB
Release files / llama_index_tools_praisonai-0.1.0.tar.gz
| Download URL | llama_index_tools_praisonai-0.1.0.tar.gz |
|---|---|
| Size | 5.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5647398e8ce5a458f53e7efd07a525a2fec813a0d40c5b4b0aae75b43572c500
|
|
BLAKE2b-256 checksum How to use checksums |
03adf4890f9b7c8e4726454b49d6b6af9bc39c5345be9ae183b997c974ad8d58
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.11
|
Release files / llama_index_tools_praisonai-0.1.0-py3-none-any.whl
| Download URL | llama_index_tools_praisonai-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
168451012dc126dd62c3c5541d8c94607e7a83d3299685739663769b98c498fe
|
|
BLAKE2b-256 checksum How to use checksums |
767304dbdaddf73413e421b2fe3ee337a778a9ff673066314ff4d4c80ea53ac9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.11
|