vichShir

Experimental Setup for LMQL with Hugging Face

We will set up an LMQL environment with Hugging Face models using Docker.

LMQL is a query language for large language models (LLMs). It facilitates LLM interaction by combining the benefits of natural language prompting with the expressiveness of Python. With only a few lines of LMQL code, users can express advanced, multi-part and tool-augmented LM queries, which then are optimized by the LMQL runtime to run efficiently as part of the LM decoding loop.

Prerequisites

Docker

"The no-GPU version was tested to work on Ubuntu 22.04 and macOS 13.2 Ventura or Windows 10 via WSL2."

Otherwise, you may have to run an Ubuntu image with Docker:

vichShir

from gensim.models.phrases import Phrases, Phraser

documents = ["o prefeito de nova iorque esteve aqui!",
             "machine learning pode ser útil às vezes...",
             "nova iorque é uma cidade muito grande",
             "o que é machine learning?",
             "machine learning é fascinante!"]

# Split
sentence_stream = [doc.split(" ") for doc in documents]

vichShir

from gensim.models.word2vec import Word2Vec
from gensim.models import KeyedVectors

pret_model_path = 'cbow_s50.txt'
my_corpus = [['machine_learning', 'gensim'], ['big_data', 'hadoop']]

# New model
w2v_model = Word2Vec(size=50, min_count=1, workers=1, sg=0, seed=1)
w2v_model.build_vocab(my_corpus)
w2v_model.vocabulary.min_count = 0

vichShir

!wget "https://docs.google.com/uc?export=download&id=FID" -O filename.csv

vichShir

How to execute SQL Server Stored Procedures in PHP

1. Connect to SQL Server (PDO)

$conn = new PDO("sqlsrv:Server=localhost,1433;Database=database_name", "username", "your_strong_password");

2. Prepare the Stored Procedure Command

$sth = $conn->prepare("SET NOCOUNT ON; EXEC stored_procedure_name ?, ?, ?;");