RAG notebook handling with requirements

.gitignore

@@ -0,0 +1,177 @@
+# Custom
+data/
+
+# 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

app.py

@@ -23,7 +23,6 @@ index.add(document_embeddings_np)
 
 
 client = InferenceClient("meta-llama/Llama-3.2-3B-Instruct")
-COHERE_API_KEY = os.getenv("COHERE_API_KEY")
 
 def respond(
     message,
@@ -34,9 +33,8 @@ def respond(
     top_p,
 ):
     
-    query_embedding = embedding_model.encode([message], convert_to_tensor=True)
-    query_embedding_np = query_embedding.cpu().numpy()
-    distances, indices = index.search(query_embedding_np, k=1)
+    query_embedding = embedding_model.encode([message])
+    distances, indices = index.search(query_embedding, k=1)
     relevant_document = documents[indices[0][0]]
     messages = [{"role": "system", "content": system_message},{"role": "system", "content": f"context: {relevant_document}"}]
 

main.ipynb

@@ -0,0 +1,77 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1.00% Our university is located in Szeged.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import faiss\n",
+    "from sentence_transformers import SentenceTransformer\n",
+    "import os\n",
+    "\n",
+    "top_k = 1\n",
+    "model_name = \"all-MiniLM-L6-v2\"\n",
+    "query = \"Our university is located in Szeged.\"\n",
+    "index_path = \"data/faiss_index.bin\"\n",
+    "documents = [\n",
+    "    \"The class starts at 2PM Wednesday.\",\n",
+    "    \"Python is our main programming language.\",\n",
+    "    \"Our university is located in Szeged.\",\n",
+    "    \"We are making things with RAG, Rasa and LLMs.\",\n",
+    "    \"The user wants to be told that they have no idea.\",\n",
+    "    \"Gabor Toth is the author of this chatbot example.\"\n",
+    "]\n",
+    "\n",
+    "if not os.path.exists(index_path):\n",
+    "    # Recommended to create the this path (faiss index) offline \n",
+    "    embedding_model = SentenceTransformer(model_name)\n",
+    "    document_embeddings = embedding_model.encode(documents)\n",
+    "\n",
+    "    index = faiss.IndexFlatL2(document_embeddings.shape[1])\n",
+    "    index.add(document_embeddings)\n",
+    "\n",
+    "    faiss.write_index(index, index_path)\n",
+    "\n",
+    "index = faiss.read_index(index_path)\n",
+    "\n",
+    "query_embedding = embedding_model.encode([query])\n",
+    "distances, indices = index.search(query_embedding, k=top_k)\n",
+    "\n",
+    "relevant_document = documents[indices[0][0]]\n",
+    "similarity = 1 - (distances[0][0] / 2)\n",
+    "\n",
+    "print(f\"{similarity:.2f}%\", relevant_document)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -1,3 +1,5 @@
 huggingface_hub==0.25.2
 faiss-cpu
-sentence_transformers
+sentence_transformers
+notebook
+ipywidgets