Skip to main content

An LLM tool for an even easier use of AiiDA.

Project description

verdi-llm


Repository Logo

Uses LLM to achieve a prompt via aiida cli

Installation

At the moment only developer installation is available. Just fetch the repo and run

pip install -e .

Usage

For now, it only works with Groq, because it provides free API. More backends will be added later.

First, configure for once: verdi-llm configure --backend groq --api-key <API-KEY> -- to generate a key see here

Now you can ask whatever you want, the limit is your imagination :crossed_fingers: $ verdi-llm cli 'delete are groups that start with label qe*'

It will then, respond with a generated command and asks for a confirmation (e) before executing it.

$ verdi-llm cli 'delete are groups that start with label qe*'
Generated command: `verdi group delete --startswith qe`

Execute[e], Modify[m], or Cancel[c]:: e
$ verdi process list
Command output:

Report: all groups deleted.

Alternatively the user has the option (m) to edit the command and fix mistakes before executing. Or simply press c to cancel.

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

verdi_llm-0.1.0.tar.gz (34.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

verdi_llm-0.1.0-py3-none-any.whl (36.5 kB view details)

Uploaded Python 3

File details

Details for the file verdi_llm-0.1.0.tar.gz.

File metadata

  • Download URL: verdi_llm-0.1.0.tar.gz
  • Upload date:
  • Size: 34.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.0

File hashes

Hashes for verdi_llm-0.1.0.tar.gz
Algorithm Hash digest
SHA256 dbc629ca7ddab843771353f5012928c629b605a66511eae5e78db02e37ab1b03
MD5 7571c29a189a19df6f452c79e21ad43d
BLAKE2b-256 07a18a75d2b663db6f57cc17c88e25afefad2d8f07900d2bd98dba034f71660a

See more details on using hashes here.

File details

Details for the file verdi_llm-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: verdi_llm-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 36.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.0

File hashes

Hashes for verdi_llm-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 eef5ea115a00c7834ed151c78679cfccefff3ffb8f652c5fd054621ec561b61b
MD5 b089ee48aa4e6b6f220a7a12437ffde6
BLAKE2b-256 d4e97a58f19ec4b8a2d74bb3d37bc849d6726a8c1b738d6a36d890c15420e4a7

See more details on using hashes here.

Supported by

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