Plegas Gerasimos makispl

## validate_gpt.py
# Set the API Key, either by setting the env var or editing it directly here:
openai_api_key = [YOUR_OPENAI_KEY]

# Create a new prompter using any desired model (GPT-3.5)and add the query_results
prompt_text = "Summarize the criticality provisions"
print (f"\n > Prompting LLM with '{prompt_text}'")
prompter = Prompt().load_model("gpt-3.5-turbo", api_key=openai_api_key)
sources = prompter.add_source_query_results(query_res)

# Prompt the LLM with the sources and query string

## rag.py
embedded_text = ''
for q in query_res:
   embedded_text += '\n'.join(q['text'].split("\'\'"))


# check all of the pertinent HuggingFace models for performance
models = ["llmware/bling-1b-0.1",
             "llmware/bling-1.4b-0.1",
             "llmware/bling-falcon-1b-0.1",
             "llmware/bling-cerebras-1.3b-0.1",

## semantic_search.py
# Construct the query
query = 'What is defined as criticality?'
query_res = Query(library).semantic_query(query, result_count=2)
print(query_res)

## embeddings.py
# Create vector embeddings for the library and store them in Milvus
# Opt for the industry-bert-asset-management model which is trained for our domain
library.install_new_embedding(embedding_model_name="industry-bert-asset-management", vector_db="milvus")

## milvus_db.py
# Create a library and load it with llmware samples
library = Library().create_new_library("Project_lib")
library.add_files([REPLACE_WITH_DOCS_PATH])

## test_query.py
# Create a test library and load it with llmware samples
test_library = Library().create_new_library("Agreements")
samples_path = Setup().load_sample_files()
test_library.add_files(os.path.join(samples_path,"Agreements"))

# Create vector embeddings for the library and store them in Milvus
test_library.install_new_embedding(embedding_model_name="industry-bert-contracts", vector_db="milvus")

# Perform a semantic search in the test library
os.environ["TOKENIZERS_PARALLELISM"] = "false" # HuggingFace tokenizer warning to be avoided

## import.py
# import dependencies
import os
import time
from llmware.library import Library
from llmware.retrieval import Query
from llmware.prompts import Prompt
from llmware.setup import Setup

## docker_compose.bash
curl -o docker-compose.yaml https://raw.githubusercontent.com/llmware-ai/llmware/main/docker-compose.yaml
docker compose up -d

## install.py
# Install transformers
pip install transformers

# Install llmware
pip install llmware

## popular_wrappers.csv

          
            Feature
            TensorFlow
            PyTorch
            Scikit-Learn

            
              Ease of Use
              Moderate complexity and extensive documentation
              Pythonic and intuitive
              Beginner-friendly & straightforward

            
              Flexibility
              High supports both high & low-level APIs
              Dynamic computation graph
              Focused on simplicity & less flexible

            
              Community Support
              Extensive and large community
              Strong community especially in research
              Well-established supportive community

            
              Use Case Versatility
              Broad range of machine learning tasks
              Research and dynamic networks
              Classic machine learning tasks
	# Set the API Key, either by setting the env var or editing it directly here:
	openai_api_key = [YOUR_OPENAI_KEY]

	# Create a new prompter using any desired model (GPT-3.5)and add the query_results
	prompt_text = "Summarize the criticality provisions"
	print (f"\n > Prompting LLM with '{prompt_text}'")
	prompter = Prompt().load_model("gpt-3.5-turbo", api_key=openai_api_key)
	sources = prompter.add_source_query_results(query_res)

	# Prompt the LLM with the sources and query string
	embedded_text = ''
	for q in query_res:
	embedded_text += '\n'.join(q['text'].split("\'\'"))


	# check all of the pertinent HuggingFace models for performance
	models = ["llmware/bling-1b-0.1",
	"llmware/bling-1.4b-0.1",
	"llmware/bling-falcon-1b-0.1",
	"llmware/bling-cerebras-1.3b-0.1",
	# Construct the query
	query = 'What is defined as criticality?'
	query_res = Query(library).semantic_query(query, result_count=2)
	print(query_res)
	# Create vector embeddings for the library and store them in Milvus
	# Opt for the industry-bert-asset-management model which is trained for our domain
	library.install_new_embedding(embedding_model_name="industry-bert-asset-management", vector_db="milvus")
	# Create a library and load it with llmware samples
	library = Library().create_new_library("Project_lib")
	library.add_files([REPLACE_WITH_DOCS_PATH])
	# Create a test library and load it with llmware samples
	test_library = Library().create_new_library("Agreements")
	samples_path = Setup().load_sample_files()
	test_library.add_files(os.path.join(samples_path,"Agreements"))

	# Create vector embeddings for the library and store them in Milvus
	test_library.install_new_embedding(embedding_model_name="industry-bert-contracts", vector_db="milvus")

	# Perform a semantic search in the test library
	os.environ["TOKENIZERS_PARALLELISM"] = "false" # HuggingFace tokenizer warning to be avoided
	# import dependencies
	import os
	import time
	from llmware.library import Library
	from llmware.retrieval import Query
	from llmware.prompts import Prompt
	from llmware.setup import Setup
	curl -o docker-compose.yaml https://raw.githubusercontent.com/llmware-ai/llmware/main/docker-compose.yaml
	docker compose up -d
	# Install transformers
	pip install transformers

	# Install llmware
	pip install llmware
Feature	TensorFlow	PyTorch	Scikit-Learn
Ease of Use	Moderate complexity and extensive documentation	Pythonic and intuitive	Beginner-friendly & straightforward
Flexibility	High supports both high & low-level APIs	Dynamic computation graph	Focused on simplicity & less flexible
Community Support	Extensive and large community	Strong community especially in research	Well-established supportive community
Use Case Versatility	Broad range of machine learning tasks	Research and dynamic networks	Classic machine learning tasks