RAG Simplified!! 🐣

AI
├── ML (Machine Learning)
│   ├── LLM (Large Language Models)
│   └── RAG (Retrieval-Augmented Generation)

 pip3 install llmware

def hello_world_questions():

    """ This is a set of useful test questions to do a 'hello world' but there is nothing special about the
    questions - please feel free to edit and ask your own queries with your own context passages.

    --if you are using one of the llmware models, please take note that the models have been trained to answer
    based on the information provided, so if you ask a question without passing any context passage, then
    don't be surprised if the model responds with 'Not Found.' """

    test_list = [

    {"query": "What is the total amount of the invoice?",
     "answer": "$22,500.00",
     "context": "Services Vendor Inc. \n100 Elm Street Pleasantville, NY \nTO Alpha Inc. 5900 1st Street "
                "Los Angeles, CA \nDescription Front End Engineering Service $5000.00 \n Back End Engineering"
                " Service $7500.00 \n Quality Assurance Manager $10,000.00 \n Total Amount $22,500.00 \n"
                "Make all checks payable to Services Vendor Inc. Payment is due within 30 days."
                "If you have any questions concerning this invoice, contact Bia Hermes. "
                "THANK YOU FOR YOUR BUSINESS!  INVOICE INVOICE # 0001 DATE 01/01/2022 FOR Alpha Project P.O. # 1000"},

    {"query": "What was the amount of the trade surplus?",
     "answer": "62.4 billion yen ($416.6 million)",
     "context": "Japan’s September trade balance swings into surplus, surprising expectations"
                "Japan recorded a trade surplus of 62.4 billion yen ($416.6 million) for September, "
                "beating expectations from economists polled by Reuters for a trade deficit of 42.5 "
                "billion yen. Data from Japan’s customs agency revealed that exports in September "
                "increased 4.3% year on year, while imports slid 16.3% compared to the same period "
                "last year. According to FactSet, exports to Asia fell for the ninth straight month, "
                "which reflected ongoing China weakness. Exports were supported by shipments to "
                "Western markets, FactSet added. — Lim Hui Jie"}
]

    return test_list

import time
from llmware.prompts import Prompt
from llmware.models import ModelCatalog

def fast_start_prompting  (model_name):

    """ This is the main example script - it loads the question list, loads the model, and executes the prompts. """

    t0 = time.time()

    # load in the 'hello world' test questions above
    test_list = hello_world_questions()

    print(f"\n > Loading Model: {model_name}...")

    prompter = Prompt().load_model(model_name)

    t1 = time.time()
    print(f"\n > Model {model_name} load time: {t1-t0} seconds")

    for i, entries in enumerate(test_list):
        print(f"\n{i+1}. Query: {entries['query']}")

        #   run the prompt
        output = prompter.prompt_main(entries["query"],
                                      context=entries["context"],
                                      prompt_name="default_with_context",
                                      temperature=0.30)

        #   'output' is a dictionary with two keys - 'llm_response' and 'usage'
        #   --'llm_response' is the output from the model
        #   --'usage' is a dictionary with the usage stats

        llm_response = output["llm_response"].strip("\n")
        print(f"LLM Response: {llm_response}")

        #   note: the 'gold answer' is the answer we provided above in the hello_world question list
        print(f"Gold Answer: {entries['answer']}")

        print(f"LLM Usage: {output['usage']}")

    t2 = time.time()
    print(f"\nTotal processing time: {t2-t1} seconds")

    return 0


if __name__ == "__main__":

    #   Step 1 - we will pick a model from the ModelCatalog

    #   A few useful methods to discover and display a list of available models...

    #   all generative models
    llm_models = ModelCatalog().list_generative_models()

    #   if you only want to see the local models
    llm_local_models = ModelCatalog().list_generative_local_models()

    #   to see only the open source models
    llm_open_source_models = ModelCatalog().list_open_source_models()

    #   we will print out the local models
    for i, models in enumerate(llm_local_models):
        print("models: ", i, models["model_name"], models["model_family"])

    #   for purposes of demo, try a few selected models from the list

    #   each of these pytorch models are ~1b parameters and will run reasonably fast and accurate on CPU
    #   --per note above, may require separate pip3 install of: torch and transformers
    pytorch_generative_models = ["llmware/bling-1b-0.1", "llmware/bling-tiny-llama-v0", "llmware/bling-falcon-1b-0.1"]

    #   bling-answer-tool is 1b parameters quantized
    #   bling-phi-3-gguf is 3.8b parameters quantized
    #   dragon-yi-6b-gguf is 6b parameters quantized
    gguf_generative_models = ["bling-answer-tool", "bling-phi-3-gguf","llmware/dragon-yi-6b-gguf"]

    #   by default, we will select a gguf model requiring no additional imports
    model_name = gguf_generative_models[0]

    #   to swap in a GPT-4 openai model - uncomment these two lines
    #   model_name = "gpt-4"
    #   os.environ["USER_MANAGED_OPENAI_API_KEY"] = "<insert-your-openai-key>"

    fast_start_prompting(model_name)

python fast_start_rag.py