update midterm

.chainlit/config.toml

@@ -0,0 +1,84 @@
+[project]
+# Whether to enable telemetry (default: true). No personal data is collected.
+enable_telemetry = true
+
+# List of environment variables to be provided by each user to use the app.
+user_env = []
+
+# Duration (in seconds) during which the session is saved when the connection is lost
+session_timeout = 3600
+
+# Enable third parties caching (e.g LangChain cache)
+cache = false
+
+# Follow symlink for asset mount (see https://github.com/Chainlit/chainlit/issues/317)
+# follow_symlink = false
+
+[features]
+# Show the prompt playground
+prompt_playground = true
+
+# Process and display HTML in messages. This can be a security risk (see https://stackoverflow.com/questions/19603097/why-is-it-dangerous-to-render-user-generated-html-or-javascript)
+unsafe_allow_html = false
+
+# Process and display mathematical expressions. This can clash with "$" characters in messages.
+latex = false
+
+# Authorize users to upload files with messages
+multi_modal = true
+
+# Allows user to use speech to text
+[features.speech_to_text]
+    enabled = false
+    # See all languages here https://github.com/JamesBrill/react-speech-recognition/blob/HEAD/docs/API.md#language-string
+    # language = "en-US"
+
+[UI]
+# Name of the app and chatbot.
+name = "Chatbot"
+
+# Show the readme while the conversation is empty.
+show_readme_as_default = true
+
+# Description of the app and chatbot. This is used for HTML tags.
+# description = ""
+
+# Large size content are by default collapsed for a cleaner ui
+default_collapse_content = true
+
+# The default value for the expand messages settings.
+default_expand_messages = false
+
+# Hide the chain of thought details from the user in the UI.
+hide_cot = false
+
+# Link to your github repo. This will add a github button in the UI's header.
+# github = ""
+
+# Specify a CSS file that can be used to customize the user interface.
+# The CSS file can be served from the public directory or via an external link.
+# custom_css = "/public/test.css"
+
+# Override default MUI light theme. (Check theme.ts)
+[UI.theme.light]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.light.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+# Override default MUI dark theme. (Check theme.ts)
+[UI.theme.dark]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.dark.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+
+[meta]
+generated_by = "0.7.700"

.gitignore

@@ -0,0 +1,160 @@
+# 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/

app.py

@@ -44,35 +44,27 @@ prompt = ChatPromptTemplate.from_messages(messages)
 chain_type_kwargs = {"prompt": prompt}
 
 
-def generate_vdb(chunks=None):
+def generate_vdb(chunks):
     EMBEDDING_MODEL = "text-embedding-3-small"
     embeddings = OpenAIEmbeddings(model=EMBEDDING_MODEL)
-    PERSIST_PATH = "./qdrant_vector_db"  # Directory to store Qdrant collection
-    COLLECTION_NAME = "legal_data"
+    LOCATION = ":memory:"
+    COLLECTION_NAME = "legal data"
     VECTOR_SIZE = 1536
 
-    # Check if the vector database already exists
-    if os.path.exists(PERSIST_PATH):
-        print(f"Loading existing Qdrant database from {PERSIST_PATH}")
-        qdrant_client = QdrantClient(path=PERSIST_PATH)  # Load the existing DB
-        qdrant_vector_store = QdrantVectorStore(
-            client=qdrant_client,
-            collection_name=COLLECTION_NAME,
-            embedding=embeddings,
-        )
-    else:
-        print(f"Creating new Qdrant database at {PERSIST_PATH}")
-        qdrant_client = QdrantClient(path=PERSIST_PATH)  # Create a new DB
-        qdrant_client.create_collection(
-            collection_name=COLLECTION_NAME,
-            vectors_config=VectorParams(size=VECTOR_SIZE, distance=Distance.COSINE),
-        )
-        qdrant_vector_store = QdrantVectorStore(
-            client=qdrant_client,
-            collection_name=COLLECTION_NAME,
-            embedding=embeddings,
-        )
-        qdrant_vector_store.add_documents(chunks)
+    qdrant_client = QdrantClient(LOCATION)
+
+    qdrant_client.create_collection(
+        collection_name=COLLECTION_NAME,
+        vectors_config=VectorParams(size=VECTOR_SIZE, distance=Distance.COSINE),
+    )
+
+    qdrant_vector_store = QdrantVectorStore(
+        client=qdrant_client,
+        collection_name=COLLECTION_NAME,
+        embedding=embeddings,
+    )
+
+    qdrant_vector_store.add_documents(chunks)
     return qdrant_vector_store
 
 
@@ -87,12 +79,11 @@ async def on_chat_start():
     "https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf",
     "https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf"]
 
-    if not os.path.exists("./qdrant_vector_db"):
-        documents = []
-        for pdf_link in pdf_links:
-            loader = PyMuPDFLoader(pdf_link)
-            loaded_docs = loader.load()
-            documents.extend(loaded_docs)
+    documents = []
+    for pdf_link in pdf_links:
+        loader = PyMuPDFLoader(pdf_link)
+        loaded_docs = loader.load()
+        documents.extend(loaded_docs)
 
         CHUNK_SIZE = 1000
         CHUNK_OVERLAP = 200
@@ -105,8 +96,6 @@ async def on_chat_start():
         split_chunks = text_splitter.split_documents(documents)
 
         docsearch = generate_vdb(split_chunks)
-    else:
-        docsearch = generate_vdb()
 
     # Let the user know that the system is ready
     msg = cl.Message(