Skip to main content

llama-index agent lats integration

Project description

Language Agent Tree Search (LATS) Agent

This agent integration implements the Language Agent Tree Search method introduced in the paper titled "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models" by Zhou et al. 2023.

We have a full cookbook on using the LATS agent here: https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/agent/lats_agent.ipynb.

Check out the source paper: https://arxiv.org/pdf/2310.04406.pdf

Usage

LATS is implemented as a BaseAgentWorker and as such is used with an AgentRunner.

from llama_index.agent.lats import LATSAgentWorker
from llama_index.core.agent import AgentRunner

tools = ...
llm = ...
agent_worker = LATSAgentWorker(tools=tools, llm=llm)
agent = AgentRunner(agent_worker)

agent.chat(...)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llama_index_agent_lats-0.3.0.tar.gz (5.9 kB view details)

Uploaded Source

Built Distribution

llama_index_agent_lats-0.3.0-py3-none-any.whl (6.5 kB view details)

Uploaded Python 3

File details

Details for the file llama_index_agent_lats-0.3.0.tar.gz.

File metadata

  • Download URL: llama_index_agent_lats-0.3.0.tar.gz
  • Upload date:
  • Size: 5.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.11.10 Darwin/22.3.0

File hashes

Hashes for llama_index_agent_lats-0.3.0.tar.gz
Algorithm Hash digest
SHA256 2b37ec3925b01a5c3c24b504fc29a6cf0d836053d37837d4a5508c51cee28c32
MD5 267a173b76e827bcebdaa3ed0541c18a
BLAKE2b-256 58e0d78a3bac7d5a9e985e1bfb1a2b3b9dd3f6035a6f3b87c89c4b5aa7650c9a

See more details on using hashes here.

File details

Details for the file llama_index_agent_lats-0.3.0-py3-none-any.whl.

File metadata

File hashes

Hashes for llama_index_agent_lats-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fb670acca40dbaceaeeb6b32a1865c8c46edd3592e8cf4b592d91f5ef3fb8efa
MD5 13ee0ea5af6ea02eb2d0da22cb351cf7
BLAKE2b-256 e31a73a8a94d1528a64134a164190406c73b750833dc8d6073e4d79d014d8b4f

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page