Project description

A minimalistic LLM agent for Exploratory Data Analysis (EDA) using pandas library

Using LangChain routers/tagging, a prompt type will be established: to produce a plot or to compute the numerical values.
The GPT model breaks down the user's request into several subtasks.
The LLM generates code based on these subtasks.
The code is executed using the python REPL.
If the REPL throws an error, GPT will begin debugging until resolved.
The result is the string output of the code 'print(result)' + optionally, saved image with a plot.

Query example: 'Find correlation between GDP and happiness index, subtract 0.4 and multiply by 1e6.'

alt text

These details have not been verified by PyPI

This version

0.1.14

Dec 14, 2023

0.1.13

Dec 2, 2023

0.1.12

Nov 23, 2023

0.1.11

Nov 23, 2023

0.1.0

Nov 22, 2023

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

Uploaded Dec 14, 2023 Source

Uploaded Dec 14, 2023 Python 3

Details for the file agenttobenamed-0.1.14.tar.gz.

Download URL: agenttobenamed-0.1.14.tar.gz
Upload date: Dec 14, 2023
Size: 9.2 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: poetry/1.7.1 CPython/3.10.12 Linux/5.15.133.1-microsoft-standard-WSL2

Details for the file agenttobenamed-0.1.14-py3-none-any.whl.

Download URL: agenttobenamed-0.1.14-py3-none-any.whl
Upload date: Dec 14, 2023
Size: 10.4 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: poetry/1.7.1 CPython/3.10.12 Linux/5.15.133.1-microsoft-standard-WSL2

Hashes for agenttobenamed-0.1.14-py3-none-any.whl
Algorithm	Hash digest
SHA256	`1dfe38c63a7893eefc3c7c5e0703fbba0f5257e42a436c3d6d58867aef890796`
MD5	`37f909667aa1ab0a1f5ccb21fa39a8f3`
BLAKE2b-256	`4d55bb63997eb32e9ff67fbf4d32b5e13f00b5e5db9f1a47225005564c7a2fdd`