Let’s Get Building🤖 – So you know the basics around OpenAI but where to from here?

git clone https://github.com/baldacchino/AzureOpenAI-LetsBuild.git

root@Baldacchino-SurfaceLaptop4:~# git clone https://github.com/baldacchino/AzureOpenAI-LetsBuild.git
Cloning into 'AzureOpenAI-LetsBuild'...
remote: Enumerating objects: 129, done.
remote: Counting objects: 100% (22/22), done.
remote: Compressing objects: 100% (15/15), done.
remote: Total 129 (delta 9), reused 6 (delta 6), pack-reused 107
Receiving objects: 100% (129/129), 257.18 KiB | 1.20 MiB/s, done.
Resolving deltas: 100% (41/41), done.
root@Baldacchino-SurfaceLaptop4:~#

pip install -r requirements.txt

Collecting azure-identity==1.6.0
  Using cached azure_identity-1.6.0-py2.py3-none-any.whl (108 kB)
Collecting streamlit==1.18.1
  Using cached streamlit-1.18.1-py2.py3-none-any.whl (9.6 MB)
Collecting openai>=0.27.1
  Downloading openai-0.27.8-py3-none-any.whl (73 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 73.6/73.6 KB 2.5 MB/s eta 0:00:00
Collecting python-dotenv==0.21.0
  Using cached python_dotenv-0.21.0-py3-none-any.whl (18 kB)
Collecting numpy
  Downloading numpy-1.24.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 17.3/17.3 MB 11.0 MB/s eta 0:00:00
Collecting pandas
  Downloading pandas-2.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 12.3/12.3 MB 10.8 MB/s eta 0:00:00
Collecting matplotlib==3.6.3
  Using cached matplotlib-3.6.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.8 MB)
Collecting plotly==5.12.0
  Using cached plotly-5.12.0-py2.py3-none-any.whl (15.2 MB)
Collecting scipy==1.10.0
  Using cached scipy-1.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (34.4 MB)
Collecting scikit-learn==1.2.0
  Using cached scikit_learn-1.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.5 MB)
Collecting tenacity
  Using cached tenacity-8.2.2-py3-none-any.whl (24 kB)
Collecting tiktoken==0.3.0
  Using cached tiktoken-0.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB)
Collecting llama-index==0.4.33
  Using cached llama_index-0.4.33-py3-none-any.whl
Collecting langchain==0.0.129
  Using cached langchain-0.0.129-py3-none-any.whl (467 kB)
Collecting faiss-cpu
  Using cached faiss_cpu-1.7.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.6 MB)
Collecting cryptography>=2.1.4
  Downloading cryptography-41.0.1-cp37-abi3-manylinux_2_28_x86_64.whl (4.3 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.3/4.3 MB 10.2 MB/s eta 0:00:00

OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
OPENAI_API_BASE=https://your-end-poiunt.openai.azure.com/

import os
import tiktoken
import openai
import numpy as np
import pandas as pd
from dotenv import load_dotenv
from openai.embeddings_utils import cosine_similarity


# Load environment variables
load_dotenv()

openai.api_type = "azure"
openai.api_base = os.environ.get("OPENAI_API_BASE")
openai.api_key = os.environ.get("OPENAI_API_KEY")
openai.api_version = "2022-12-01"

# Define embedding model and encoding
EMBEDDING_MODEL = 'text-embedding-ada-002'
COMPLETION_MODEL = 'text-davinci-003'
encoding = tiktoken.get_encoding('cl100k_base')

print("--- Start : Testing Completition ---")
response = openai.Completion.create(engine="text-davinci-003",
                                    prompt="Knock knock.",
                                    temperature=0)
print(response.choices[0].text)
print("--- Complete : Testing Completion ---")
print("")
print("--- Start : Testing Completion Streaming ---")
import sys
for resp in openai.Completion.create(engine='text-davinci-003', prompt='Give me 10 taglines for an ice cream shop', max_tokens=512, stream=True):
    sys.stdout.write(resp.choices[0].text)
    sys.stdout.flush()
print("--- Complete : Testing Completion Streaming ---")
print("")
print("--- Start : Testing Embeddings ---")
e = openai.Embedding.create(input="Hello World!", engine=EMBEDDING_MODEL)["data"][0]["embedding"]
print(e)
print("--- Start : Testing Tokeniser ---")
tokens = encoding.encode("Hello world!")
print(tokens)
print(len(tokens))
print("--- Tokeniser : Testing Tokeniser ---")

 streamlit run chatgpt_app.py
  You can now view your Streamlit app in your browser.
  Local URL: http://localhost:8501
  Network URL: http://172.26.106.84:8501

import os
import json
import tiktoken
import openai
import numpy as np
from dotenv import load_dotenv
from openai.embeddings_utils import cosine_similarity
from tenacity import retry, wait_random_exponential, stop_after_attempt

# Load environment variables
load_dotenv()

# Configure Azure OpenAI Service API
openai.api_type = "azure"
openai.api_version = "2022-12-01"
openai.api_base = os.getenv('OPENAI_API_BASE')
openai.api_key = os.getenv("OPENAI_API_KEY")

# Define embedding model and encoding
EMBEDDING_MODEL = 'text-embedding-ada-002'
EMBEDDING_ENCODING = 'cl100k_base'
EMBEDDING_CHUNK_SIZE = 8000
COMPLETION_MODEL = 'text-davinci-003'

# initialize tiktoken for encoding text
encoding = tiktoken.get_encoding(EMBEDDING_ENCODING)

# list all files the samples directory
samples_dir = os.path.join(os.getcwd(), "../data/qna/")
sample_files = os.listdir(samples_dir)

# read each file and remove and newlines (better for embeddings later)
documents = []
for file in sample_files:
    with open(os.path.join(samples_dir, file), "r") as f:
        content = f.read()
        content = content.replace("\n", " ")
        content = content.replace("  ", " ")
        documents.append(content)

# print some stats about the documents
print(f"Loaded {len(documents)} documents")
for doc in documents:
    num_tokens = len(encoding.encode(doc))
    print(f"Content: {doc[:80]}... \n---> Tokens: {num_tokens}\n")

@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))
def get_embedding(text):
    return openai.Embedding.create(input=text, engine=EMBEDDING_MODEL)["data"][0]["embedding"]

# Create embeddings for all docs
embeddings = [get_embedding(doc) for doc in documents]

# print some stats about the embeddings
for e in embeddings:
    print(len(e))

# create embedding for question
question = "what is azure openai service?"
qe = get_embedding(question)

# calculate cosine similarity between question and each document
similaries = [cosine_similarity(qe, e) for e in embeddings]

# Get the matching document, in this case we just use argmax of similarities
max_i = np.argmax(similaries)

# print some stats about the similarities
for i, s in enumerate(similaries):
    print(f"Similarity to {sample_files[i]} is {s}")
print(f"Matching document is {sample_files[max_i]}")

# Generate a prompt that we use for completion, in this case we put the matched document and the question in the prompt
prompt = f"""
Content:
{documents[max_i]}
Please answer the question below using only the content from above. If you don't know the answer or can't find it, say "I couldn't find the answer".
Question: {question}
Answer:"""

# get response from completion model
response = openai.Completion.create(
    engine=COMPLETION_MODEL,
    prompt=prompt,
    temperature=0.7,
    max_tokens=500,
    top_p=1,
    frequency_penalty=0,
    presence_penalty=0,
    stop=None
)
answer = response['choices'][0]['text']

# print the question and answer
print(f"Question was: {question}\nRetrieved answer was: {answer}")

python3 qna_with_embeddings.py 
Loaded 3 documents
Content:  # What is conversational language understanding? Conversational language unders... 
---> Tokens: 1341
Content:  # What is Azure OpenAI? The Azure OpenAI service provides REST API access to Op... 
---> Tokens: 1891
Content:  # What is Azure Cognitive Services Translator? Translator Service is a cloud-ba... 
---> Tokens: 739
1536
1536
1536
Similarity to overview_clu.txt is 0.7739850962131803
Similarity to overview_openai.txt is 0.8674998947964985
Similarity to overview_translator.txt is 0.7914908142869009
Matching document is overview_openai.txt
Question was: what is azure openai service?
Retrieved answer was:  Azure OpenAI Service provides REST API access to OpenAI's powerful language models including the GPT-3, Codex and Embeddings model series. Users can access the service through REST APIs, Python SDK, or our web-based interface in the Azure OpenAI Studio.

openai.error.InvalidRequestError: The response was filtered due to the prompt triggering Azure OpenAI’s content management policy. Please modify your prompt and retry. To learn more about our content filtering policies please read our documentation: https://go.microsoft.com/fwlink/?linkid=2198766

python3 movie_classification.py 
(715, 12)
Test would cost $0.016750800000000003 for embeddings
(715, 1536)
Cluster 0 topics: love, family, divorce
Movies from cluster 0: Guess Who, Trainwreck, In Her Shoes, Wedding Crashers, After Hours, Morning Glory, Isn't It Romantic, The Family Stone, Meet the Fockers, My Best Friend's Wedding, Click, Bridget Jones's Diary, Mrs. Doubtfire, Nappily Ever After, The Farewell, Punch-Drunk Love, City Lights, The Switch, Confessions of a Shopaholic, The Big Sick, The Wedding Planner, Major League, The Upside, Splash, Definitely, Maybe
================
Cluster 1 topics: Family, love, comedy.
Movies from cluster 1: Yours, Mine & Ours, Herbie Fully Loaded, Playing with Fire, Short Circuit, Bill & Ted Face the Music, Grown Ups 2, Dr. Dolittle 2, Beethoven, Liar Liar, Paddington, Harold & Kumar Go to White Castle, Gremlins 2: The New Batch, Christmas with the Kranks, Twins, Young Frankenstein, Borat Subsequent Moviefilm, Your Highness, The Kings of Summer, Chef, As Good as It Gets, The Dukes of Hazzard, Swiss Army Man, A Haunted House 2, American Pie Presents: Band Camp, Little Evil
================
Cluster 2 topics: Ghostbusters, Embezzle, Detective
Movies from cluster 2: Clerks, Brazil, The Waterboy, Analyze That, The Big Lebowski, Evolution, Patch Adams, In Bruges, A Fish Called Wanda, Anchorman 2: The Legend Continues, Adaptation., Tenacious D in The Pick of Destiny, Piranha 3D, White Chicks, Deuce Bigalow: Male Gigolo, Charlie Wilson's War, Meet Dave, Eddie the Eagle, Kiss Kiss Bang Bang, The Other Guys, Life of Brian, Observe and Report, Muppets Most Wanted, Police Academy 2: Their First Assignment, Zombieland
================