Ecosyste.ms: Summary

https://github.com/soheil-mp/Llama2

Fine-tuning the Llama2 model

fine-tuning llama2 llm

Last synced: 15 Nov 2026

https://github.com/danielgrittner/llama2-rs

LLaMA2 + Rust

ai deep-learning llama2 llama2c llm llm-inference rust

Last synced: 15 Nov 2026

https://github.com/meta-introspector/gbnf-nice-parser

llama.cpp gbml Menhir parser in OCaml

gbnf grammar llama2 llamacpp

Last synced: 15 Nov 2026

https://github.com/its-joseph-230606/LlamaGPT

LlamaV2 is a friendly and free chatbot created by Meta.

ai android api artificial-intelligence bot chatbot gpt gpt-3 huggingface lightweight llama2 neural-network nlp physics pydroid python science terminal termux

Last synced: 15 Nov 2026

https://github.com/hsleonis/llama3_qa_chatbot_mongodb

Llama3 in MongoDB: Conversational QA App with Langchain + Ollama + MongoDB + Streamlit.

chatbot chatgpt deep-learning langchain large-language-models llama2 llama3 machine-learning mongodb natural-language-processing ollama openai python streamlit

Last synced: 15 Nov 2026

https://github.com/sendbird/sendbird-live-sdk-ios

Sendbird Live API turns a client app into a live streaming platform where users can broadcast themselves in real-time to their followers.

api-for-live bard broadcast chatbot-api chatgpt communications-platform conversation ios-sdk live-event live-sdk live-streaming llama2 messaging-platform palm2 rtc streaming swift-sdk voip webrtc

Last synced: 15 Nov 2026

https://github.com/zhangleinice/chatbot

llama2聊天机器人

langchain llama2

Last synced: 15 Nov 2026

https://github.com/agnivchtj/python_rag_app

Implementing a local RAG pipeline that processes PDFs and lets users query information from these documents using LLMs.

chroma chromadb llama2 llm nomic-embed-text ollama python rag

Last synced: 15 Nov 2026

https://github.com/tairov/lamatune

LLama implementations benchmarking framework

benchmark llama2

Last synced: 15 Nov 2026

https://github.com/leoneversberg/codellama-chatbot

A local LLM chatbot using Code Llama

chatbot code-llama deep-learning llama2 llm nlp streamlit

Last synced: 15 Nov 2026

https://github.com/BorjaOteroFerreira/IALab-Suite

Tool for test diferents large language models without code.

api-rest chat-application flask-api inference-api large-language-models llama-cpp-python llama2 llama2-7b llamacpp llm llm-inference local-inference mixtral-8x7b

Last synced: 15 Nov 2026

https://github.com/rajat709/Llama2-7b-Medical-Model

Fine Tuned Meta Llama2 7b Model Curated for Medical Purpose, https://huggingface.co/rjvishwa/Llama-2-7b-Med-Model/tree/main

apps fine-tuning gradio llama2 llm medical

Last synced: 15 Nov 2026

https://github.com/craigsdennis/scairy

Uses AI to scare people...more.

ai blip2 elevenlabs halloween llama2 replicate sadtalker

Last synced: 15 Nov 2026

https://github.com/BlackLionXD/personal-data-assistant

A chatbot that summarizes and analyzes PDF documents using Llama 2, Flask, and LangChain. Subsequently, you can post questions to the chatbot regarding the PDF's contents and get answers...

chatbot flask generative-ai langchain-python llama2 retrival-augmented-generation

Last synced: 15 Nov 2026

https://github.com/EvilFreelancer/MoDA

Is a framework designed to enhance the performance and flexibility of large language models by dynamically selecting and integrating specialized LoRA adapters based on the input query.

adapters gpt llama2 lora router transformers

Last synced: 15 Nov 2026

https://github.com/farhan0167/llama-engine

High level Python API to run open source LLM models on Colab with less code

llama2 llm

Last synced: 15 Nov 2026

https://github.com/LLM-Semantic-Router/vllm-router

vLLM Router

huggingface kubernetes llama2 llm llm-inference vllm

Last synced: 15 Nov 2026

https://github.com/silvanmelchior/IncognitoPilot

An AI code interpreter for sensitive data, powered by GPT-4 or Code Llama / Llama 2.

ai chatgpt chatgpt-code-interpreter codellama copilot gpt-4 llama2 llm python

Last synced: 15 Nov 2026

https://github.com/jellyterra/ideallama

Coding assistant powered by LLaMA 2! Project ends up. Please choose Continue.dev

code-completion intellij llama2

Last synced: 15 Nov 2026

https://github.com/b4rtaz/distributed-llama

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

distributed-computing distributed-llm llama2 llama3 llm llm-inference llms neural-network open-llm

Last synced: 14 Nov 2026

https://github.com/emilsharkov/ChatGPTAPIClone

This is a scalable and fault tolerant API cluster that answers prompts similarly to ChatGPT, built with Terraform and Python

aws docker-image kubernetes llama2 python terraform

Last synced: 15 Nov 2026

https://github.com/milinddeore/ner-anon-mode

This model facilitates both data anonymization and the incorporation of synthetic data.

anonymization llama2 llm named-entity-recognition ner synthetic-data

Last synced: 15 Nov 2026

https://github.com/AquibPy/Genify

Genify is a powerful and versatile API that leverages advanced language models, including Google's Gemini 1.5 Pro, LLAMA 3 and other cutting-edge technologies, to deliver a wide range of natural language processing capabilities

fastapi gemini-api gemini-pro gemini-pro-1-5 gemini-pro-vision generative-ai llama-index llama2 llama3 mistral-7b mongodb openllm palm-api python3 retrieval-augmented-generation

Last synced: 15 Nov 2026

https://github.com/kirteshpatel98/RegHub_news_signal_analysis

ai bert-model deep-learning generative-ai large-language-models llama2 named-entity-recognition natural-language-processing similarity-analysis

Last synced: 15 Nov 2026

https://github.com/lopezjhonf/Easy_NLP

This repository will save any code related to NLP and LLM models for chatbots or task instructions, such as BERT, DISTILLBERT, LLAMA2, MISTRAL, T5, etc.

bert distilbert llama2 llm mistral-7b

Last synced: 15 Nov 2026

https://github.com/ariful-eu/Green-Code-Guardians

An empirical comparative study on energy efficiency of LLMs (ChatGPT, Bard, Llama2) associated User Interfaces.

bard chatgpt green-lab llama2 llm llm-ui llm-user-interface user-interface vrije-universiteit-amsterdam

Last synced: 15 Nov 2026

https://github.com/iltoga/WebSummarizer

Ai driven - command line tool to perform goal-based web searches

ai ai-search ai-web-search example-project goal-based-search langchain langchain-python learn-ai llama2 llm python-ai search summarization web zephyr

Last synced: 15 Nov 2026

https://github.com/chaoluond/safetyllama

Finetune LLaMA-2-7b-chat to perform safety evaluation of user-bot conversation

chatbot chatgpt-api chatgpt3 finetune-llm integrity-protection llama2 machine-learning safety

Last synced: 15 Nov 2026

https://github.com/arham-kk/llama2-qlora-sft

This model is a fine-tuned model based on the "TinyPixel/Llama-2-7B-bf16-sharded" model and "timdettmers/openassistant-guanaco" dataset

bitsandbytes fine-tuning language-model llama2 llm nlp peft qlora quantization transformers

Last synced: 15 Nov 2026

https://github.com/avk1943/Blog-Generation-LLM-App

A Generative AI web application that generates content for blogs

langchain llama2 python streamlit-webapp

Last synced: 15 Nov 2026

https://github.com/nanofuxion/buni

Buni is a TypeScript-based client API for Ollama, designed to be simple yet flexible.

ai bun bunjs javascript llama2 module ollama ollama-api typescript

Last synced: 15 Nov 2026

https://github.com/odynvolk/jensen

A LLM powered Telegram chatbot.

chatbot llama2 llamacpp llm telegram

Last synced: 15 Nov 2026

https://github.com/SourasishBasu/ChatPDF-clone-llama2b

Chatbot app for interactively conversing with PDFs

astradb chatbot gradientai llama2 llama2-7b llm meta python streamlit-webapp vector-database

Last synced: 15 Nov 2026

https://github.com/enoch1118/ollamaGUI

Ollama app for macos

ai llama2 llm mac macos ollama swift swiftui

Last synced: 15 Nov 2026

https://github.com/smendes2901/movie_chat_bot

This repository contains the implementation of a fine-tuned Llama2 chatbot using QLoRA, tailored to provide detailed information and recommendations about movies. The model is fine-tuned on the IMDB dataset, enabling it to generate informed and contextually relevant responses.

chatbot embeddings fine-tuning huggingface instruction-tuning llama2 llm pandas pytorch recommender-system sentence vector

Last synced: 15 Nov 2026

https://github.com/unikraft/app-llama2-c

Llama 2 Everywhere (L2E)

llama2 unikernel unikraft-application

Last synced: 15 Nov 2026

https://github.com/being-invincible/LlamaHairSense

Elevate your hair care journey with HairSense: a transformative project uniting Clarifai's advanced vision AI and Llama 2's perceptive prowess. Effortlessly decipher your hair's distinct nature through imagery, unlocking custom-tailored solutions that redefine hair care precision

ai haircare healthcare llama2 python streamlit

Last synced: 15 Nov 2026

https://github.com/QpxDesign/TREC-iKAT

An attempt of the iKAT (Interactive Knowledge Assistance Track) Track of the 2023 run of the NIST's TREC.

ai bert fastchat-t5 information-retrieveal llama2 llm nist sentance-transformers trec-ikat

Last synced: 15 Nov 2026

https://github.com/mgokulkrish/LENR.ai

Github Repo for Recommendation System using LLMs.

fine-tuning llama2 llm mistral-7b recommender-system

Last synced: 15 Nov 2026

https://github.com/flyfir248/Jina-webapp

Jina-embeddings-v2 is an English text embedding model by Jina AI, based on Bert architecture, with an 8192-sequence length, outperforming OpenAI's embedding model in various metrics

artificial-intelligence embeddings jina llama2 meta

Last synced: 15 Nov 2026

https://github.com/breitburg/dart-ollama

Use Ollama's LLMs directly from Dart

ai large-language-models ollama

Last synced: 15 Nov 2026

https://github.com/himannshusharma/CHATBOT

CREATE A CHATBOT USING LANGCHAIN WITH OPENSOURSE AI OLLAMA

langchain llama2 llm ollama streamlit

Last synced: 15 Nov 2026

https://github.com/KleinYuan/llama2-csv-webapp

self host/local host llama2 based web app to chat with your csvs (multiple)

chatgpt csv datalake large-language-models llama2 llm meta openai pandas pandas-ai pandasai streamlit

Last synced: 15 Nov 2026

https://github.com/WackyGem/Nicol

Nicol is an open-source web service, developed using the Kotlin programming language, that enables streaming Server Stream Events and supports CPU inference for the port of llama2 model.

gradle jimmer kotlin llama2 spring-boot

Last synced: 15 Nov 2026

https://github.com/MarioCSilva/RAG_QA_LLM

Knowledge-Sharing Hub using RAG Q&A techniques with LLMs (Llama2 and ChatGPT)

chatgpt genai langchain llama2 llamaindex llm openai question-answering rag

Last synced: 15 Nov 2026

https://github.com/KompleteAI/xllm

🦖 X—LLM: Simple & Cutting Edge LLM Finetuning

alpaca cerebras chatgpt deep-learning deep-neural-networks deeplearning falcon gpt language-model large-language-models llama2 llama2-7b llm mistal mistral mistralai natural-language-processing nlp openai vicuna

Last synced: 15 Nov 2026

https://github.com/jalvarezz13/summarAI

SummarAI utilizes PyMovie and Whisper to transcribe videos, enabling you to ask questions about the content using Llama2 and Llama-index for insightful interaction.

llama-index llama2 pymovie whisper

Last synced: 15 Nov 2026

https://github.com/Ivang71/ai-content-waterfall

Generate website articles with ai

generative-ai llama2

Last synced: 15 Nov 2026

https://github.com/sendbird/sendbird-chat-sample-ios

This repository provides feature-level Chat samples with Swift.

api-for-chat bard chat-api chat-api-platform chat-platform chat-sdk chatbot-api chatbot-sdk chatgpt communications-platform genai-chatbot genai-chatbot-api genai-chatbot-sdk gpt-powered-chatbot instant-messaging-api llama2 messaging-api messaging-platform messaging-sdk palm2

Last synced: 15 Nov 2026

https://github.com/jaywyawhare/PDFIntellect

Streamline PDF data retrieval with PDFIntellect, harnessing the intelligence of LLMs via an intuitive Streamlit interface.

llama2 llm nlp vector-database

Last synced: 15 Nov 2026

https://github.com/Abstract-Dex/Document-Chatbot

Small document chatbot using LlamaIndex and Llama-2

chromadb langchain llama2 llamaindex pytorch sentence-transformers text-generation

Last synced: 15 Nov 2026

https://github.com/sanogotech/Llama-2-Streamlit-Chatbot

LangChain , LIama , Streamlit app that demonstrates a conversational chat

artificial-intelligence chatbot chatgpt csv-parser ia langchain llama2 streamlit

Last synced: 15 Nov 2026

https://github.com/JuliaMerz/pantry

Actor based multi-llm registry + runner.

ggml llama2 llm rust

Last synced: 15 Nov 2026

https://github.com/DantasB/revAisor

A repository built to store the final project for the PESC LLM Applications (COS836)

experimentation gpt llama2 llms survey

Last synced: 15 Nov 2026

https://github.com/mddunlap924/LangChain-SynData-RAG-Eval

LangChain, Llama2-Chat, and zero- and few-shot prompting are used to generate synthetic datasets for IR and RAG system evaluation

few-shot information-retrieval langchain llama2 llm nlp prompt prompt-engineering prompts-template question-answering rag retrieval-augmented-generation

Last synced: 15 Nov 2026

https://github.com/verifai/multiLLM

🚀 Invoke multiple large language models concurrently and the rank results. Add new models and ranking functions quickly.. ⭐

api bard chatgpt large-language-models llama2

Last synced: 15 Nov 2026

https://github.com/MajidRaimi/Chat-With-PDF

Small project where you can chat with pdf using langchain framework.

chroma langchain llama2 llm python

Last synced: 15 Nov 2026

https://github.com/0xDing/yuren-13b

Yuren 13B is an information synthesis large language model that has been continuously trained based on Llama 2 13B, which builds upon the data-centric work of Pleisto.

llama2 llm synth-ai transformer

Last synced: 15 Nov 2026

https://github.com/Garrachonr/LlamaDos

Finetuning of a Llama2-7B to give it the ability of having a fluent conversation in Spanish.

ai conversational finetuning llama2 nlp spanish

Last synced: 15 Nov 2026

https://github.com/dromzeh/cf-workers-hono-llama2

Simple skeleton for llama-2 integration within a Cloudflare Worker alongside Hono using Typescript and Zod for extra form validation.

cloudflare cloudflare-workers hono llama2 typescript zod

Last synced: 15 Nov 2026

https://github.com/lgrammel/modelfusion-llamacpp-nextjs-starter

Starter examples for using Next.js and the Vercel AI SDK with Llama.cpp and ModelFusion.

ai llama2 llamacpp mistral modelfusion next nextjs vercel-ai vercel-ai-sdk

Last synced: 15 Nov 2026

https://github.com/crazycheetah42/GyanAI

The open-source AI-powered productivity assistant.

ai assistant gyanai linux llama2 open-source python replicate windows

Last synced: 15 Nov 2026

https://github.com/suryanshgupta9933/Law-GPT

Chatbot for Indian Law using Llama-7B-chat using Langchain integration and Streamlit UI.

gpt indian-law langchain langchain-python law llama2 llm streamlit vectorstore

Last synced: 15 Nov 2026

https://github.com/iohub/collama

VSCode AI coding assistant powered by self-hosted llama.cpp endpoint.

ai-assistant code-generation cody copilot llama2 llamacpp vscode-extension

Last synced: 15 Nov 2026

https://github.com/nrimsky/CAA

Steering Llama 2 with Contrastive Activation Addition

llama2 pytorch

Last synced: 15 Nov 2026

https://github.com/j-webtek/Private-Llama2-File-Chat

This is a chatbot, powered by an LLM (Llama2), which embeds your data into a vector store. You are then able to query your LLM on your private data

chatbot llama2 local private

Last synced: 15 Nov 2026

https://github.com/jorge-armando-navarro-flores/chat-with-multiple-PDFs-LLAMA2

This script is a chat application that allows users to ask questions about multiple PDF documents implemented with meta's LLAMA2

chat-with-pdf faiss langchain llama2 llms python

Last synced: 15 Nov 2026

https://github.com/yihong1120/Traffic-Violation-Report-System

A platform for users to upload and share the responses from law enforcement agencies to their traffic violation reports in Taiwan. This system aims to increase transparency and public oversight of traffic law enforcement.

big-query cloud-computing computer-vision database-design django gcp gemini google-maps-api llama2 machine-learning nginx python raspberry-pi taiwan ubuntu web-development yolov8

Last synced: 15 Nov 2026

https://github.com/joreilly86/structual_llama

Assistant for structural engineering design and analysis, with emphasis on Python code assistance. Built off llama2-13b.

ai civil-engineering llama2 python structural-engineering

Last synced: 15 Nov 2026

https://github.com/pew/slack-workers-ai

Cloudflare Workers AI llama2 Slack Bot

cloudflare cloudflare-workers cloudflare-workers-ai llama2

Last synced: 15 Nov 2026

https://github.com/codingstark-dev/llama-hono-cloudflare

cloudflare-ai cloudflare-workers hono honojs llama2 llama3

Last synced: 15 Nov 2026

https://github.com/yihong1120/Llama2-Telegram-Bot

Integration of the advanced llama2 AI model with Telegram to provide real-time chatbot responses. Seamless interaction, smart replies, and scalable deployment.

ai asyncio chatbot django docker integration llama2 llamacpp nlp python real-time-interactions scalable-applications telegram-bot

Last synced: 15 Nov 2026

https://github.com/kazcfz/LlamaIndex-RAG-Chat

Perform RAG (Retrieval-Augmented Generation) from your PDFs using this Colab notebook! Powered by Llama 2

ai chatbot colab colab-notebook huggingface llama-index llama2 llamacpp llm openllm rag retrieval-augmented-generation transformers

Last synced: 15 Nov 2026

https://github.com/stop1one/GRAPHENE

Data Science Application III (DATA410) Final Project

data-science large-language-models llama2 llama2-7b llm

Last synced: 15 Nov 2026

https://github.com/ictnlp/SiLLM

SiLLM is a Simultaneous Machine Translation (SiMT) Framework. It utilizes a Large Language model as the translation model and employs a traditional SiMT model for policy-decision to achieve SiMT through collaboration.

chatgpt large large-language-models llama2 machine-translation simultaneous-machine-translation translation

Last synced: 15 Nov 2026

https://github.com/shaimaaK/LLM-playground

Large Language Model Playground : experiment with Llama2, Falcon, GPT 3.5 Turbo , and Flan chat LLM and tune LLM parameters

chatbot gpt35turbo large-language-models llama2 llama2-13b llama2-70b llm streamlit

Last synced: 15 Nov 2026

https://github.com/mrdbourke/mac-ml-speed-test

A few quick scripts focused on testing TensorFlow/PyTorch/Llama 2 on macOS.

apple-silicon benchmark deep-learning llama2 llamacpp llm m1 m1-mac m2-mac m3-mac machine-learning macos metal metal-performance-shaders ml mps pytorch speedtest tensorflow2

Last synced: 15 Nov 2026

https://github.com/neel1996/lagoon

Llama2 + Supabase powered tool to ingest and chat with github documents

generative-ai llama2 llms supabase

Last synced: 15 Nov 2026

https://github.com/mBerezovskyy/LlamaMedicalQA

From scratch implementation of QA over a multiple documents, scraped from the American cancer society website.

chromadb ctranslate2 llama2 open-source retreivalqa

Last synced: 15 Nov 2026

https://github.com/rootint/llm-pmldl

NeuraLearn is a project aimed to enhance the knowledge base and accessibility of Large Language Models (LLMs) for Machine Learning engineers.

ai llama2 ml rag

Last synced: 15 Nov 2026

https://github.com/curiousily/Get-Things-Done-with-Prompt-Engineering-and-LangChain

LangChain & Prompt Engineering tutorials on Large Language Models (LLMs) such as ChatGPT with custom data. Jupyter notebooks on loading and indexing data, creating prompt templates, CSV agents, and using retrieval QA chains to query the custom data. Projects for using a private LLM (Llama 2) for chat with PDF files, tweets sentiment analysis.

artificial-intelligence chatgpt deep-learning gpt-4 gpt4 langchain language-models large-language-models llama2 openai prompt-engineering python

Last synced: 15 Nov 2026

https://github.com/arafkarsh/ms-springboot-ai

Java 23, SpringBoot 3.4.1 Examples using Deep Learning 4 Java & LangChain4J for Generative AI using ChatGPT LLM, RAG and other open source LLMs. Sentiment Analysis, Application Context based ChatBots. Custom Data Handling. LLMs - GPT 3.5 / 4o, Gemini Pro 1.5, Claude 3, Llama 3.1, Phi-3, Gemma 2, Falcon 3, Qwen 2.5, Mistral Nemo, Wizard Math

chatgpt3 chatgpt4 claude-3 convolutional-neural-network falcon gemini gemini-ai gemma gemma-7b generative-ai langchain langchain4j llama2 mistral-7b multilayer-perceptron-network ollama qwen2-5 rag recurrent-neural-network retrieval-augmented-generation

Last synced: 15 Nov 2026

https://github.com/ZeusSama0001/RAG-chatbot

RAG chatbot using Llama 2, chainlit and Faiss

chainlit faiss huggingface langchain llama2 llama2-7b pypdf2

Last synced: 15 Nov 2026

https://github.com/ehsanghaffar/llm-practice

A self-hosted personal chatbot API with FastAPI & Langchain, It allows you to interact with the Llama2 LLM (and other open-source LLMs) to have natural language conversations, generate text, and perform various language-related tasks.

langchain langserve langsmith langsmith-deployments llama2 llamacpp llm-serving

Last synced: 15 Nov 2026

https://github.com/PRAKALP-PANDE/Llama-2

Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.

large llama2 mongodb python streamlit

Last synced: 15 Nov 2026

https://github.com/xanmoy/medinova

The MediNova AI is a powerful tool designed to provide medical information by answering user queries using state-of-the-art language models and vector stores.

ai bot chainlit ctransformers faiss langchain llama2 medical python sentence-transformers

Last synced: 15 Nov 2026

https://github.com/LogitsAI/beta

Home of the Logits public beta program

kubernetes llama2 llm

Last synced: 15 Nov 2026

https://github.com/BlackLionXD/LectureSummarizer

LectureSummarizer is an AI-powered website that transcribes and summarizes lectures. It uses OpenAI Whisper for accurate speech-to-text and Llama 2 for concise summaries. With an easy-to-use Gradio interface, it helps students capture and review key lecture points efficiently.

generative-ai-projects gradio llama2 openai-whisper torch

Last synced: 15 Nov 2026

https://github.com/ag2307/CSV-GPT

Document Question Answering Chatbot

csv docx langchain llama2 llm openai pdf streamlit txt

Last synced: 15 Nov 2026

https://github.com/thillai-c/MediQuill-llama2

A model fine tuned on llama-2 to solve medical queries

llama2 llm medicine

Last synced: 15 Nov 2026

https://github.com/Oldentomato/LocalLLM_ChatbotSystem

bert-embeddings bm25 fastapi llama2 llm

Last synced: 15 Nov 2026

https://github.com/kedir/Specialized-Immigration-Assistant

provide specialized immigration assistance in the field of immigration law using large language model

bitsandbytes huggingface-hub huggingface-transformers large-language-models llama2 nlp-machine-learning numpy peft python pythorch transformer transformer-reinforcement-learning

Last synced: 15 Nov 2026

https://github.com/chiaramanna/data_augmentation_LLaMA2

Exploring prompt-based data augmentation by leveraging LLaMA2

data-augmentation llama2 prompt

Last synced: 15 Nov 2026

https://github.com/ebowwa-archive/LLM_telecenter

A fastapi wrapper of babca / python-gsmmodem for a waveshare sim7600x. Not an exact copy of the 'python-gsmmodem' so be sure to uninstall that lib or venv to run | Open-source Twilio with LLM batteries

agentgpt deepgram elevenlabs elevenlabs-api gsm gsm-modem gsm-module langchain langchain-python llama2 llamacpp mistral-7b mistralai oai openai openai-api pyserial raspberry-pi salesgpt whisper