Skip to main content

A lightweight Ollama(no ollama installation needed) based LangChain-compatible LLM bridge ('LLaMA-3.2','CodeLLaMA-Instruct 7B','Gemma-2-Instruct 9B','Mistral 7B Instruct','Qwen-2.5-Coder 7B','Phi-3 Medium (8B)','Falcon 7B Instruct','Baichuan-2-7B','InternLM-Chat-7B','Vicuna 7B') built by Sonu Kumar.

Project description

npmai

npmai (by Sonu Kumar Ramashish) is a lightweight Python package that seamlessly connects you with Ollama and other open-source models without any Installation, Login/Signup or API problems.

🚀 Features

Execute prompts on multiple LLMs simultaneously:["LLaMA-3.2","CodeLLaMA-Instruct 7B","Gemma-2-Instruct 9B","Mistral 7B Instruct","Qwen-2.5-Coder 7B","Phi-3 Medium (8B)","Falcon 7B Instruct","Baichuan-2-7B","InternLM-Chat-7B","Vicuna 7B"]

Fully LangChain,CrewAI and other -compatible interface.

Simple and intuitive invoke() API for instant responses.

Support continuous conversation.

Encourages responsible usage.

⚙️ Installation pip install npmai

Tip: For Python 3.13, make sure to use:

py -3.13 -m pip install npmai

💡 How to Use

Import the models

from npmai import Ollama

Initialize Ollama:

llm = Ollama()

prompts="" model="Llama3.2" you can keep other also

Invoke a prompt and get the response:

response = llm.invoke(prompts,model) print(response)

#Latest Update : version 0.0.8 Here you will get Ollama's 10 model.

⚠️ Important Notes

Designed for educational ,small-scale experimentation, for demo projets and small scale users.

If using at a larger scale, consider supporting the original AI platforms—they invest heavily in research and infrastructure.

use responsibly to help us.

✅ npmai makes it effortless to connect Ollam models with Python, bringing automation, experimentation, and LangChain,Crew AI integration together in a single, easy-to-use package.

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

npmai-0.0.8.tar.gz (3.1 kB view details)

Uploaded Source

Built Distribution

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

npmai-0.0.8-py3-none-any.whl (3.3 kB view details)

Uploaded Python 3

File details

Details for the file npmai-0.0.8.tar.gz.

File metadata

  • Download URL: npmai-0.0.8.tar.gz
  • Upload date:
  • Size: 3.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for npmai-0.0.8.tar.gz
Algorithm Hash digest
SHA256 41f70da1522310f06493a0e414b2b47ed2157149001e17f3c39a78ef8883b4a1
MD5 5af0c3ddffdedb29581ef2a9857f8c32
BLAKE2b-256 12b487894e0afea72e8131b53ebd111b136dd7bced27468995be78ca95a572de

See more details on using hashes here.

File details

Details for the file npmai-0.0.8-py3-none-any.whl.

File metadata

  • Download URL: npmai-0.0.8-py3-none-any.whl
  • Upload date:
  • Size: 3.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for npmai-0.0.8-py3-none-any.whl
Algorithm Hash digest
SHA256 af34f1e45f8ac83402f342369ebe376f45bc9d3ba15ed53d52feb4b2740f416d
MD5 fff0adc14f799fb5a4f81f5d9837ed95
BLAKE2b-256 bfe57cd1cc32a27ea54cc8cc3e7874afc2c15f0eb6d9daebc100b40a236802d8

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