Perform Semantic Search using Chroma vector DB

vector-chromadb/.gitignore

@@ -0,0 +1,163 @@
+# 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/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/
+venv-app/
+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/

vector-chromadb/main.py

@@ -0,0 +1,66 @@
+import chromadb
+from chromadb.utils import embedding_functions
+import json
+
+import csv
+import os
+
+
+# Store the csv files line to a array
+documents = []
+# Store the metadata to a array
+metadatas = []
+# Store the unique id to a array
+ids = []
+
+#Load csv file
+if os.path.exists('menu-items.csv'):
+    print('File exists')
+    # Open the CSV file for reading
+    with open('menu-items.csv', 'r') as file:
+        # Create a CSV reader object
+        reader = csv.reader(file)
+        id=1
+        # # Iterate over each row in the CSV
+        # Iterate over each row in the csv using reader object
+        for i, line in enumerate(reader):
+            # Skip the header row
+            if i == 0:
+                continue
+            # Add the document, metadata and id to the respective arrays
+            documents.append(line[1])
+            metadatas.append({'item_id': line[0]})
+            ids.append(str(id))
+            id+=1
+
+
+# print(documents)
+# create the Chroma Client
+# client = chromadb.Client()
+client = chromadb.PersistentClient(path='my_vectordb')
+sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction("all-mpnet-base-v2")
+collection = client.get_or_create_collection("menu-items", embedding_function=sentence_transformer_ef)
+
+# add the documents to the collection
+collection.add(documents=documents, metadatas=metadatas, ids=ids)
+
+# Query mispelled words
+results = collection.query(
+    query_texts=["sphagetti"],
+    n_results=5,
+    include=["documents", "distances","metadatas"]
+)
+print(results['documents'])
+
+results = collection.query(
+    query_texts=["chicken"],
+    n_results=5,
+    include=["documents", "distances","metadatas"]
+)
+print(results['documents'])
+results = collection.query(
+    query_texts=["shrimp"],
+    n_results=5,
+    include=["documents", "distances","metadatas"]
+)
+print(f"Search Result for shrimp:\n{results['documents']}")