Upload 9 files

.gitignore

@@ -0,0 +1,174 @@
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc

Dockerfile

@@ -0,0 +1,18 @@
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim
+
+RUN useradd -m -u 1000 user
+USER user
+
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH \
+    UVICORN_WS_PROTOCOL=websockets
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+RUN uv sync
+
+EXPOSE 7860
+
+CMD ["uv", "run", "chainlit", "run", "app.py", "--host", "0.0.0.0", "--port", "7860"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Aneeta Xavier
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

app.py

@@ -0,0 +1,60 @@
+import os
+import json
+from langchain_core.documents import Document
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_openai import ChatOpenAI
+from langchain.chains import RetrievalQA
+import chainlit as cl
+
+# === Load and prepare data ===
+with open("combined_data.json", "r") as f:
+    raw_data = json.load(f)
+
+all_docs = [
+    Document(page_content=entry["content"], metadata=entry["metadata"])
+    for entry in raw_data
+]
+
+# === Split documents into chunks ===
+splitter = RecursiveCharacterTextSplitter(chunk_size=800, chunk_overlap=50)
+chunked_docs = splitter.split_documents(all_docs)
+
+# === Use your fine-tuned Hugging Face embeddings ===
+embedding_model = HuggingFaceEmbeddings(
+    model_name="AneetaXavier/reformer-pilates-embed-ft-49fc1835-9968-433d-9c45-1538ea91dcc9"
+)
+
+# === Set up FAISS vector store ===
+vectorstore = FAISS.from_documents(chunked_docs, embedding_model)
+retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
+
+# === Load LLM ===
+llm = ChatOpenAI(model_name="gpt-4.1-mini", temperature=0)
+qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
+
+# === Chainlit start event ===
+@cl.on_chat_start
+async def start():
+    await cl.Message(content = 
+"""👋 Welcome to your Reformer Pilates AI!
+
+Here’s what you can do:
+• Ask questions about Reformer Pilates
+• Get individualized workouts based on your level, goals, and equipment
+• Get instant exercise modifications based on injuries or limitations
+
+Let’s get started! 🚀""").send()
+    cl.user_session.set("qa_chain", qa_chain)
+
+# === Chainlit message handler ===
+@cl.on_message
+async def handle_message(message: cl.Message):
+    chain = cl.user_session.get("qa_chain")
+    if chain:
+        try:
+            response = chain.run(message.content)
+        except Exception as e:
+            response = f"⚠️ Error: {str(e)}"
+        await cl.Message(response).send()

chainlit.md

@@ -0,0 +1,14 @@
+# Welcome to Chainlit! 🚀🤖
+
+Hi there, Developer! 👋 We're excited to have you on board. Chainlit is a powerful tool designed to help you prototype, debug and share applications built on top of LLMs.
+
+## Useful Links 🔗
+
+- **Documentation:** Get started with our comprehensive [Chainlit Documentation](https://docs.chainlit.io) 📚
+- **Discord Community:** Join our friendly [Chainlit Discord](https://discord.gg/k73SQ3FyUh) to ask questions, share your projects, and connect with other developers! 💬
+
+We can't wait to see what you create with Chainlit! Happy coding! 💻😊
+
+## Welcome screen
+
+To modify the welcome screen, edit the `chainlit.md` file at the root of your project. If you do not want a welcome screen, just leave this file empty.

pyproject.toml

@@ -0,0 +1,22 @@
+[project]
+name = "pilates_fine_tuned"
+version = "0.1.0"
+description = "A fine-tuned pilates project."
+dependencies = [
+    "langchain-huggingface>=0.0.6",
+    "chainlit>=2.5.5",
+    "faiss-cpu>=1.11.0",
+    "langchain>=0.3.25",
+    "langchain-community>=0.3.24",
+    "langchain-openai>=0.3.16",
+    "langchain-core>=0.0.1",  # Added langchain-core
+    "pymupdf>=1.25.5",
+    "pytube>=15.0.0",
+    "unstructured>=0.17.2",
+    "youtube-transcript-api>=1.0.3",
+    "websockets==11.0.3"
+]
+
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"

test_env.py

@@ -0,0 +1,2 @@
+import os
+print("OPENAI_API_KEY:", os.getenv("OPENAI_API_KEY"))