Skip to main content

Faster and Smaller alternative to Lanchain

Project description

YakaLLM

A smaller, faster and cooler version of LangChain. the repo without .git is only 74k. Its like preact for react, but nothing is backward compatible.

how to install

pip:

pip install yaka-llm
# or 
pip3 install yaka-llm

uv:

uv add yaka-llm
# or 
uv pip install yaka-llm

Usage

from yaka_llm import GeminiModel
from yaka_llm.core import UserPrompt, ModelPrompt
import os

gm = GeminiModel("gemini-2.5-flash", os.getenv("LLM_API_KEY"))

gm.call(["Hello there"], prompt="What's up?")

# or

history = [UserPrompt("What are the three largest cities in Spain?"),
           ModelPrompt("The three largest cities in Spain are Madrid, Barcelona, and Valencia.")]
print(gm.call(history, prompt="What is the most famous landmark in the second one?"))

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

yaka_llm-1.0.0.tar.gz (6.0 kB view details)

Uploaded Source

Built Distribution

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

yaka_llm-1.0.0-py3-none-any.whl (8.4 kB view details)

Uploaded Python 3

File details

Details for the file yaka_llm-1.0.0.tar.gz.

File metadata

  • Download URL: yaka_llm-1.0.0.tar.gz
  • Upload date:
  • Size: 6.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.15 {"installer":{"name":"uv","version":"0.9.15","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for yaka_llm-1.0.0.tar.gz
Algorithm Hash digest
SHA256 55fc020ce74bc8187722274e99680fc0833872e28a921979b645a045f5a531dd
MD5 e268badbdcf67f65675aba96182eeb5b
BLAKE2b-256 da9cdf1d621177c65861610410e0ef80efdfa62a48a09cc5f9c35fabe0bd9a8e

See more details on using hashes here.

File details

Details for the file yaka_llm-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: yaka_llm-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 8.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.15 {"installer":{"name":"uv","version":"0.9.15","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for yaka_llm-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2d41cb27847cc57dae504d1c699008c063581570bccfae4b0d41d56d0419843f
MD5 37f188680b6c4409c627ed241236e895
BLAKE2b-256 8a2b48cbffae7b4b443e6bf0f570699346631d7ad9d4b780cc23062e3c3ad15c

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