Init: poetry project and mvp chadGPT app

.gitignore

@@ -0,0 +1,135 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# GPT artifacts
+*.pdf
+db/
+articles/
+index.json

pyproject.toml

@@ -0,0 +1,23 @@
+[tool.poetry]
+name = "chadgpt"
+version = "0.1.0"
+description = "chatGPT client for knowledge base"
+authors = ["MOIS3Y <stepan@zhukovsky.me>"]
+readme = "README.md"
+packages = [{include = "chadgpt", from = "src"}]
+
+[tool.poetry.dependencies]
+python = "^3.11"
+openai = "^0.27.4"
+gpt-index = "0.4.24"
+pypdf2 = "^3.0.1"
+pycryptodome = "^3.17"
+gradio = "^3.27.0"
+
+
+[tool.poetry.group.dev.dependencies]
+flake8 = "^6.0.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

src/chadgpt/main.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+import os
+import sys
+import gradio
+from dotenv import load_dotenv, find_dotenv
+from langchain.chat_models import ChatOpenAI
+from gpt_index import (
+    SimpleDirectoryReader,
+    GPTListIndex,
+    GPTSimpleVectorIndex,
+    LLMPredictor,
+    PromptHelper
+)
+
+
+def get_env():
+    if not os.environ.get("OPENAI_API_KEY"):
+        load_dotenv(find_dotenv())
+        
+
+# parse hidden api key:
+def construct_index(directory_path):
+    # promt params:
+    max_input_size = 4096
+    num_outputs = 512
+    max_chunk_overlap = 20
+    chunk_size_limit = 600
+
+    prompt_helper = PromptHelper(
+        max_input_size,
+        num_outputs,
+        max_chunk_overlap,
+        chunk_size_limit=chunk_size_limit
+    )
+
+    llm=ChatOpenAI(
+        temperature=0.7,
+        model_name="gpt-3.5-turbo",
+        max_tokens=num_outputs
+    )
+
+    llm_predictor = LLMPredictor(llm)
+
+    # get documents for learn:
+    documents = SimpleDirectoryReader(directory_path).load_data()
+
+    index = GPTSimpleVectorIndex(
+        documents,
+        llm_predictor=llm_predictor,
+        prompt_helper=prompt_helper
+    )
+
+    index.save_to_disk('index.json')
+
+    return index
+
+def chatbot(input_text):
+    index = GPTSimpleVectorIndex.load_from_disk('index.json')
+    response = index.query(input_text, response_mode="compact")
+    return response.response
+
+
+iface = gradio.Interface(
+    fn=chatbot,
+    inputs=gradio.components.Textbox(lines=7, label="Enter your text"),
+    outputs="text",
+    title="ISPsystem custom-trained AI Chatbot"
+)
+
+index = construct_index("../docs")
+
+
+def main():
+    get_env()
+    iface.launch(share=False)
+
+
+if __name__ == "__main__":
+    main()