init

.gitignore

@@ -0,0 +1,178 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python
+
+.streamlit

app.py

@@ -0,0 +1,99 @@
+import torch
+import pickle
+import streamlit as st
+from transformers import Conversation, pipeline
+from upload import get_file, upload_file
+from utils import clear_uploader, undo, restart
+
+
+share_keys = ["messages", "model_name"]
+MODELS = ["facebook/blenderbot-400M-distill", "facebook/blenderbot-90M"]
+
+st.set_page_config(
+    page_title="LLM",
+    page_icon="📚",
+)
+
+if "model_name" not in st.session_state:
+    st.session_state.model_name = "facebook/blenderbot-400M-distill"
+    
+
+def get_pipeline(model_name):
+    device = 0 if torch.cuda.is_available() else -1
+    chatbot = pipeline(model=model_name, task="conversational", device=device)
+    return chatbot
+
+chatbot = get_pipeline(st.session_state.model_name)
+
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+if len(st.session_state.messages) == 0 and "id" in st.query_params:
+    with st.spinner("Loading chat..."):
+        id = st.query_params["id"]
+        data = get_file(id, 'llm-007')
+        obj = pickle.loads(data)
+        for k, v in obj.items():
+            st.session_state[k] = v
+
+
+def share():
+    obj = {}
+    for k in share_keys:
+        if k in st.session_state:
+            obj[k] = st.session_state[k]
+    data = pickle.dumps(obj)
+    id = upload_file(data, 'llm-007')
+    url = f"https://umbc-nlp-llm.hf.space/?id={id}"
+    st.markdown(f"[share](/?id={id})")
+    st.success(f"Share URL: {url}")
+
+with st.sidebar:
+    st.title(":blue[LLM Only]")
+
+    st.subheader("Model")
+    model_name = st.selectbox("Model", MODELS, index=MODELS.index(st.session_state.model_name))
+
+    if st.button("Share", use_container_width=True):
+        share()
+
+    cols = st.columns(2)
+    with cols[0]:
+        if st.button("Restart", type="primary", use_container_width=True):
+            restart()
+    
+    with cols[1]:
+        if st.button("Undo", use_container_width=True):
+            undo()
+
+    append = st.checkbox("Append to previous message", value=False)
+
+
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+
+def push_message(role, content):
+    message = {"role": role, "content": content}
+    st.session_state.messages.append(message)
+    return message
+
+if prompt := st.chat_input("Type a message", key="chat_input"):
+    push_message("user", prompt)
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    if not append:
+        with st.chat_message("assistant"):
+            conversation = Conversation()
+            for m in st.session_state.messages:
+                conversation.add_message(m)
+            print(conversation)
+            with st.spinner("Generating response..."):
+                response = chatbot(conversation)
+                response = response[-1]["content"]
+                st.write(response)
+
+        push_message("assistant", response)
+    clear_uploader()

requirements.txt

@@ -0,0 +1,2 @@
+streamlit
+boto3

upload.py

@@ -0,0 +1,27 @@
+import streamlit as st
+import uuid
+import boto3
+
+s3 = boto3.client(
+    's3',
+    aws_access_key_id=st.secrets["AWS_ACCESS_KEY"],
+    aws_secret_access_key=st.secrets["AWS_SECRET_KEY"]
+)
+
+def upload_file(data, bucket=st.secrets["S3_BUCKET"]):
+    file_name = uuid.uuid4().hex
+    try:
+        key = f"{file_name}.pkl"
+        response = s3.put_object(Body=data, Bucket=bucket, Key=key)
+    except Exception as e:
+        return None
+    return file_name
+
+
+def get_file(file_name, bucket=st.secrets["S3_BUCKET"]):
+    try:
+        response = s3.get_object(Bucket=bucket, Key=f"{file_name}.pkl")
+        return response['Body'].read()
+    except Exception as e:
+        print(e)
+        return False

utils.py

@@ -0,0 +1,22 @@
+import time
+import streamlit as st
+
+
+def clear_uploader():
+    st.rerun()
+
+def undo():
+    if len(st.session_state.messages) > 0:
+        st.query_params.clear()
+        msg = st.session_state.messages.pop()
+        if msg["role"] == "assistant" and "cost" in st.session_state:
+            st.session_state.cost.pop()
+        time.sleep(0.1)
+        st.rerun()
+
+def restart():
+    st.query_params.clear()
+    st.session_state.messages = []
+    st.session_state.cost = []
+    time.sleep(0.2)
+    clear_uploader()