Add Docker files and scripts for DockerAI integration

.gitignore

@@ -0,0 +1,176 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# 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/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python

README.md

@@ -0,0 +1,5 @@
+# DockerAI Gen Example
+
+This is an example of how to use DockerAI for genAI
+
+Author: David Cardozo 

docker-bot/Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.11-bullseye
+
+WORKDIR /usr/src/app
+
+COPY docker_bot /usr/src/app/docker_bot
+COPY pyproject.toml /usr/src/app/pyproject.toml
+COPY README.md /usr/src/app/README.md
+
+RUN pip install -e .
+
+EXPOSE 8504
+
+HEALTHCHECK CMD curl --fail http://localhost:8504/_stcore/health
+
+ENTRYPOINT ["streamlit", "run", "yt_whisper/app.py", "--server.port=8504", "--server.address=0.0.0.0"]

docker-bot/docker_bot/bot.py

@@ -0,0 +1,150 @@
+import os
+
+import pinecone
+import streamlit as st
+from dotenv import load_dotenv
+from openai import OpenAI
+from streamlit.logger import get_logger
+
+load_dotenv(".env")
+
+load_dotenv(".env")
+
+logger = get_logger(__name__)
+
+client = OpenAI(api_key=os.getenv("OPENAI_TOKEN"))
+
+
+@st.cache_resource
+def load_pinecone(index_name="docker-genai"):
+    # initialize pinecone
+    pinecone.init(
+        api_key=os.getenv("PINECONE_TOKEN"),
+        environment=os.getenv("PINECONE_ENVIRONMENT"),
+    )
+    if index_name not in pinecone.list_indexes():
+        # we create a new index
+        pinecone.create_index(name=index_name, metric="cosine", dimension=1536)
+    index = pinecone.Index(index_name)
+    return index
+
+
+def generate_response(input_text):
+    question_embedding = client.embeddings.create(
+        input=[input_text], model="text-embedding-ada-002"
+    )
+    num_embeddings = list(question_embedding.data[0].embedding)
+    # print(list(question_embedding.data[0].embedding))
+    res_contex = load_pinecone().query(
+        vector=num_embeddings,
+        top_k=5,
+        include_metadata=True,
+    )
+
+    matches = res_contex["matches"]
+
+    context = (
+        "The following are the top 5 videos transcription that match your query: \n"
+    )
+    references = ""
+    for match in matches:
+        context += "Title: " + match.metadata["title"] + "\n"
+        context += "Transcription: " + match.metadata["text"] + "\n"
+        references += "\n - " + match.metadata["video_url"] + "\n"
+
+    primer = """You are Q&A bot. A highly intelligent system that answers 
+    user questions based on the information provided by videos transcriptions. You can use your inner knowledge,
+    but consider more with emphasis the information provided. Put emphasis on the transcriptions provided. If you see titles repeated, you can assume it is the same video.
+    Provide samples of the transcriptions that are important to your query.
+    """
+
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {"role": "system", "content": primer},
+            {
+                "role": "user",
+                "content": context,
+            },
+            {"role": "user", "content": input_text},
+        ],
+        model="gpt-4-1106-preview",
+    )
+    response = chat_completion.choices[0].message.content
+
+    # Add video references
+    response += "\n" + references
+
+    return response
+
+
+logger = get_logger(__name__)
+
+
+# Streamlit UI
+styl = """
+<style>
+    /* not great support for :has yet (hello FireFox), but using it for now */
+    .element-container:has([aria-label="Select RAG mode"]) {{
+      position: fixed;
+      bottom: 33px;
+      background: white;
+      z-index: 101;
+    }}
+    .stChatFloatingInputContainer {{
+        bottom: 20px;
+    }}
+
+    /* Generate ticket text area */
+    textarea[aria-label="Description"] {{
+        height: 200px;
+    }}
+</style>
+"""
+st.markdown(styl, unsafe_allow_html=True)
+
+
+def chat_input():
+    user_input = st.chat_input("What you want to know about your videos?")
+
+    if user_input:
+        with st.chat_message("user"):
+            st.write(user_input)
+        with st.chat_message("assistant"):
+            st.caption("Dockerbot")
+            # result = output_function(
+            #     {"question": user_input, "chat_history": []}, callbacks=[stream_handler]
+            # )["answer"]
+            result = generate_response(user_input)
+            # result = "I am a bot. I am still learning."
+            output = result
+            st.session_state["user_input"].append(user_input)
+            st.session_state["generated"].append(output)
+            st.rerun()
+
+
+def display_chat():
+    # Session state
+    if "generated" not in st.session_state:
+        st.session_state["generated"] = []
+
+    if "user_input" not in st.session_state:
+        st.session_state["user_input"] = []
+
+    if st.session_state["generated"]:
+        size = len(st.session_state["generated"])
+        # Display only the last three exchanges
+        for i in range(max(size - 3, 0), size):
+            with st.chat_message("user"):
+                st.write(st.session_state["user_input"][i])
+
+            with st.chat_message("assistant"):
+                # st.caption(f"RAG: {st.session_state['rag_mode'][i]}")
+                st.caption("Dockerbot")
+                st.write(st.session_state["generated"][i])
+
+        with st.container():
+            st.write("&nbsp;")
+
+
+display_chat()
+chat_input()