0.3

.github/workflows/linters.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11"]
+        python-version: ["3.10", "3.11", "3.12"]
     steps:
     - name: Checkout
       uses: actions/checkout@v3

CHANGELOG.md

@@ -20,7 +20,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [0.2] - 2023-10-15
 
+### Added
+- Test generator
+- page_retriever
+
 ### Changed
 - Bumped submodules to latest versions
 - Added test project
 - Structure refactoring
+
+
+## [0.3] - 2023-11_20
+
+### Added
+- Added README.md
+- Bumped requirements
+- Removed submodules (moved to requirements - OpenAI API, Leonardo API)
+- Added python 3.12 for linting

README.md

@@ -1,2 +1,55 @@
-# ai_engines
-Playground and utils libraries for AI stuff
+# AI Engines
+
+This is playground and utils libraries for AI stuff.
+
+It is not a framework, but a collection of useful tools and examples. It's not a pinned repo, not a featured and supported, and in general violates all the best practices of software development. But it's a good place to start. At the beginning and the end of all, this repo contains stuff that I mentioned in my articles, thus, refer to [my blog](https://wwakabobik.github.io/) posts first.
+
+## What you can find here
+
+- [x] [**examples**](/examples) - a collection of examples of AI projects, including:
+  - [x] [image_generation](/examples/image_generation) - a simple example of image generation using DALLE and Leonardo
+  - [x] [speak_and_hear](/examples/speak_and_hear) - see [article](https://wwakabobik.github.io/2023/09/ai_learning_to_hear_and_speak/) first, this is LLM speech recognition and TTS example
+  - [x] [test_generator](/examples/test_generator) - see [article](https://wwakabobik.github.io/2023/10/qa_ai_practices_used_for_qa/) first, this is QA automatic tests generator
+  - [x] [llm_api_comparison](/examples/llm_api_comparison) - TBD
+- [x] [**utils**](/utils) - a collection of useful tools for AI development, in general them all of them used in example projects:
+  - [x] [article_extractor](/utils/article_extractor.py) - limbo for article extraction from web pages
+  - [x] [audio_recorder](/utils/audio_recorder.py) - a simple audio recorder, used in speech recognition / TTS examples
+  - [x] [logger_config](/utils/logger_config.py) - general logger
+  - [x] [other](/utils/other.py) - all that doesn't fit in other files, i.e. env checkers
+  - [x] [page_retriever](/utils/page_retriever.py) - web page retriever and parser
+  - [x] [transcriptors](/utils/transcriptors.py) - custom transcriptors wrappers for speech recognition
+  - [x] [translators](/utils/translators.py) - custom translators for text translation wrappers
+  - [x] [tts](/utils/tts.py) - custom TTS engines wrappers
+
+## Running up that hill
+
+Once again, refer to [my blog](https://wwakabobik.github.io/) posts first. If you do so, you may try exec some top-level scripts from parent directory:
+
+```bash
+git clone [email protected]:wwakabobik/ai_engines.git  # clone this repo
+cd ai_engines  # go to repo directory
+# It's highly recommended to use python 3.11+ and venv
+python -m venv venv  # create virtual environment
+source venv/bin/activate  # activate virtual environment
+pip install -r requirements.txt  # install dependencies
+# then you may run some top-level script, like:
+PYTHONPATH=. python -m examples.test_generator.generator_test
+PYTHONPATH=. python -m examples.speak_and_hear.test_gpt 
+```
+
+Well, in most cases you need to create cred file to run examples, so, create `creds.py` under `examples` directory and fill it with your credentials, like:
+
+```python
+# -*- coding: utf-8 -*-
+"""Creds file"""
+oai_token = "alksjdlksajlkdjlajiouoieuoqijnc"
+oai_organization = "slkahkdjshakjhfkjafs"
+cohere_token = "saklljlkdjsaldjljasldjlsak"
+llama_token="asiuoiduaosudouasosuoduoqoihicdhzch"
+ablt_token="sadhsakhdajskhaskdkja"
+claude_token="dkshjjsdhkjdshkjhskj"
+openweathermap_appid = "salkdjaslkjldasjlkdasl"
+midjourney_cookie="skjaklshkldfhkjsahjhfkjbkfsa"
+```
+
+GL&HF!

examples/llm_api_comparison/__init__.py

@@ -0,0 +1,12 @@
+# -*- coding: utf-8 -*-
+"""
+Filename: __init__.py
+Author: Iliya Vereshchagin
+Copyright (c) 2023. All rights reserved.
+
+Created: 20.11.2023
+Last Modified: 20.11.2023
+
+Description:
+This file is init file for llm_api_comparison package.
+"""

requirements.txt

@@ -9,23 +9,24 @@ SpeechRecognition==3.10.0
 # Translator
 deep_translator==1.11.4
 # Recorder
-pyaudio==0.2.13
+pyaudio==0.2.14
 sounddevice==0.4.6
 soundfile==0.12.1
-numpy==1.26.1
+numpy==1.26.2
 # Image
 pillow==10.1.0
 # Articles
 readability==0.3.1
 # Testing
 webdriver_manager==4.0.1
-selenium==4.15.1
+selenium==4.15.2
 pytest==7.4.3
 pytest-json-report==1.5.0
-pytest-xdist==3.3.1
+pytest-xdist==3.4.0
 # Third-party-test
-cohere==4.32
+cohere==4.35
 llamaapi==0.1.36
 # My AI APIs
 leonardo-api==0.0.7
 openai-python-api==0.0.5
+ablt-python-api==0.0.2