Setup Qdrant cluster

.gitignore

@@ -0,0 +1,152 @@
+# 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
+
+# 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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted 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/

Dockerfile

@@ -30,11 +30,5 @@ RUN nohup ollama serve & sleep 5
 #
 EXPOSE 7860
 
-#
-EXPOSE 6333
-
-#
-EXPOSE 6334
-
 # # Run .sh file
 ENTRYPOINT ["sh", "/code/start_service.sh"]

app/rag.py

@@ -1,3 +1,5 @@
+import logging
+
 from llama_index.core import (
     SimpleDirectoryReader,
     VectorStoreIndex,
@@ -12,8 +14,10 @@ from llama_index.embeddings.ollama import OllamaEmbedding
 from llama_index.llms.ollama import Ollama
 from llama_index.core.retrievers import VectorIndexRetriever
 from llama_index.core.indices.query.query_transform import HyDEQueryTransform
-import qdrant_client
-import logging
+from qdrant_client import QdrantClient
+
+QDRANT_API_URL = os.getenv('QDRANT_API_URL')
+QDRANT_API_KEY = os.getenv('QDRANT_API_KEY')
 
 
 class ChatPDF:
@@ -28,7 +32,7 @@ class ChatPDF:
         text_parser = SentenceSplitter(chunk_size=512, chunk_overlap=100)
 
         logger.info("initializing the vector store related objects")
-        client = qdrant_client.QdrantClient(host="localhost", port=6333)
+        client = QdrantClient(url=QDRANT_API_URL, api_key=QDRANT_API_KEY)
         vector_store = QdrantVectorStore(client=client, collection_name="rag_documents")
 
         logger.info("initializing the OllamaEmbedding")