google

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.9
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+COPY --chown=user . $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["chainlit", "run", "app.py", "--port", "7860"]
+

README.md

@@ -1,8 +1,8 @@
 ---
-title: PrepGoogle4o
-emoji: 📉
-colorFrom: green
-colorTo: pink
+title: Prepr
+emoji: 👁
+colorFrom: blue
+colorTo: gray
 sdk: docker
 pinned: false
 license: openrail

app.py

@@ -0,0 +1,113 @@
+# AI MAKERSPACE PREPR 
+# Date: 2024-5-16
+
+# Basic Imports & Setup
+import os
+from openai import AsyncOpenAI
+
+# Using Chainlit for our UI
+import chainlit as cl
+from chainlit.prompt import Prompt, PromptMessage
+from chainlit.playground.providers import ChatOpenAI
+
+# Getting the API key from the .env file
+from dotenv import load_dotenv
+load_dotenv()
+
+# RAG pipeline imports and setup code
+# Get the DeveloperWeek PDF file (future implementation: direct download from URL)
+from langchain.document_loaders import PyMuPDFLoader
+
+# Adjust the URL to the direct download format
+#file_id = "1JeA-w4kvbI3GHk9Dh_j19_Q0JUDE7hse"
+#direct_url = f"https://drive.google.com/uc?export=download&id={file_id}"
+
+file_id = "11Bq38osADZtTxGudM9OJr51BV9YwKsf3"
+direct_url = f"https://drive.google.com/uc?export=download&id={file_id}"
+
+# Now load the document using the direct URL
+docs = PyMuPDFLoader(direct_url).load()
+
+import tiktoken
+def tiktoken_len(text):
+    tokens = tiktoken.encoding_for_model("gpt-3.5-turbo").encode(
+        text,
+    )
+    return len(tokens)
+
+# Split the document into chunks
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size = 500,           # 500 tokens per chunk, experiment with this value
+    chunk_overlap = 50,        # 50 tokens overlap between chunks, experiment with this value
+    length_function = tiktoken_len,
+)
+
+split_chunks = text_splitter.split_documents(docs)
+
+# Load the embeddings model
+from langchain_openai.embeddings import OpenAIEmbeddings
+
+embedding_model = OpenAIEmbeddings(model="text-embedding-3-small")
+
+# Load the vector store and retriever from Qdrant
+from langchain_community.vectorstores import Qdrant
+
+qdrant_vectorstore = Qdrant.from_documents(
+    split_chunks,
+    embedding_model,
+    location=":memory:",
+    collection_name="Prepr",
+)
+
+qdrant_retriever = qdrant_vectorstore.as_retriever()
+
+from langchain_openai import ChatOpenAI
+openai_chat_model = ChatOpenAI(model="gpt-3.5-turbo")
+
+from langchain_core.prompts import ChatPromptTemplate
+RAG_PROMPT = """
+CONTEXT:
+{context}
+
+QUERY:
+{question}
+
+You are a personal assistant for a professional.  Your tone is professional and considerate. Before proceeding to answer about which conference sessions the user should attend, be sure to ask them what key topics they are hoping to learn from the conference, and if there are any specific sessions they are keen on attending. Use the provided context to answer the user's query. You are a professional personal assistant for an executive professional in a high tech company. You help them plan for events and meetings. You always review the provided event information. You can look up dates and location where event sessions take place from the document. If you do not know the answer, or cannot answer, please respond with "Insufficient data for further analysis, please try again". For each session you suggest, include bullet points with the session title, speaker, company, topic, AI industry relevance, details of their work in AI, main point likely to be made, and three questions to ask the speaker. You end your successful responses with "Is there anything else that I can help you with?". If the user says NO, or any other negative response, then you ask "How did I do?
+"""
+
+rag_prompt = ChatPromptTemplate.from_template(RAG_PROMPT)
+
+from operator import itemgetter
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnablePassthrough
+
+retrieval_augmented_qa_chain = (
+    {"context": itemgetter("question") | qdrant_retriever, "question": itemgetter("question")}
+    | RunnablePassthrough.assign(context=itemgetter("context"))
+    | {"response": rag_prompt | openai_chat_model, "context": itemgetter("context")}
+)
+
+# Chainlit App
+@cl.on_chat_start
+async def start_chat():
+    settings = {
+        "model": "gpt-3.5-turbo",
+        "temperature": 0,
+        "max_tokens": 500,
+        "top_p": 1,
+        "frequency_penalty": 0,
+        "presence_penalty": 0,
+    }
+    cl.user_session.set("settings", settings)
+
+@cl.on_message
+async def main(message: cl.Message):
+    chainlit_question = message.content
+    #chainlit_question = "What was the total value of 'Cash and cash equivalents' as of December 31, 2023?"
+    response = retrieval_augmented_qa_chain.invoke({"question": chainlit_question})
+    chainlit_answer = response["response"].content
+
+    msg = cl.Message(content=chainlit_answer)
+    await msg.send()

chainlit.md

@@ -0,0 +1,3 @@
+# AI Makerspace Demo Day - Prepr 
+
+Welcome to Prepr your personal preparation assistant.  I can help you prepare for a conference, a meeting or an interview ... How can I help you today?

requirements.txt

@@ -0,0 +1,206 @@
+aiofiles==23.2.1
+aiohttp==3.9.5
+aiosignal==1.3.1
+altair==5.3.0
+annotated-types==0.6.0
+anyio==3.7.1
+appdirs==1.4.4
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+async-lru==2.0.4
+asyncer==0.0.2
+attrs==23.2.0
+Babel==2.14.0
+backoff==2.2.1
+beautifulsoup4==4.12.3
+bidict==0.23.1
+bleach==6.1.0
+blinker==1.8.1
+cachetools==5.3.3
+certifi==2024.2.2
+cffi==1.16.0
+chainlit
+charset-normalizer==3.3.2
+click==8.1.7
+cohere==4.37
+contourpy==1.2.1
+curl_cffi==0.6.2
+cycler==0.12.1
+dataclasses-json==0.5.14
+datasets==2.19.0
+defusedxml==0.7.1
+Deprecated==1.2.14
+dill==0.3.8
+dirtyjson==1.0.8
+distro==1.9.0
+docker==7.0.0
+docker-pycreds==0.4.0
+duckduckgo_search==5.3.0
+fastapi==0.100.1
+fastapi-socketio==0.0.10
+fastavro==1.9.4
+fastjsonschema==2.19.1
+filelock==3.13.4
+filetype==1.2.0
+fonttools==4.51.0
+fqdn==1.5.1
+frozenlist==1.4.1
+fsspec==2024.3.1
+gitdb==4.0.11
+GitPython==3.1.43
+googleapis-common-protos==1.63.0
+grandalf==0.8
+greenlet==3.0.3
+grpcio==1.62.2
+grpcio-tools==1.62.2
+h11==0.14.0
+h2==4.1.0
+hpack==4.0.0
+httpcore==0.17.3
+httpx
+huggingface-hub==0.22.2
+hyperframe==6.0.1
+idna==3.6
+importlib-metadata==6.11.0
+install==1.3.5
+ipywidgets==8.1.2
+isoduration==20.11.0
+Jinja2==3.1.3
+joblib==1.4.0
+json5==0.9.25
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+jupyter==1.0.0
+jupyter-console==6.6.3
+jupyter-events==0.10.0
+jupyter-lsp==2.2.5
+jupyter_server==2.14.0
+jupyter_server_terminals==0.5.3
+jupyterlab
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.26.0
+jupyterlab_widgets==3.0.10
+kiwisolver==1.4.5
+langchain==0.1.17
+langchain-community==0.0.36
+langchain-core==0.1.50
+langchain-openai==0.1.6
+langchain-text-splitters==0.0.1
+langchainhub==0.1.15
+langsmith==0.1.48
+Lazify==0.4.0
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.21.1
+matplotlib==3.8.4
+mdurl==0.1.2
+mistune==3.0.2
+multidict==6.0.5
+multiprocess==0.70.16
+mypy-extensions==1.0.0
+nbclient==0.10.0
+nbconvert==7.16.3
+nbformat==5.10.4
+networkx
+nltk==3.8.1
+notebook==7.1.2
+notebook_shim==0.2.4
+numpy==1.26.4
+openai==1.25.1
+opentelemetry-api==1.24.0
+opentelemetry-exporter-otlp==1.24.0
+opentelemetry-exporter-otlp-proto-common==1.24.0
+opentelemetry-exporter-otlp-proto-grpc==1.24.0
+opentelemetry-exporter-otlp-proto-http==1.24.0
+opentelemetry-instrumentation==0.45b0
+opentelemetry-proto==1.24.0
+opentelemetry-sdk==1.24.0
+opentelemetry-semantic-conventions==0.45b0
+orjson==3.10.1
+overrides==7.7.0
+packaging==23.2
+pandas==2.2.2
+pandocfilters==1.5.1
+pillow==10.3.0
+plotly==5.22.0
+portalocker==2.8.2
+prometheus_client==0.20.0
+protobuf==4.25.3
+pyarrow==16.0.0
+pyarrow-hotfix==0.6
+pycparser==2.22
+pydantic==2.6.4
+pydantic_core==2.16.3
+pydeck==0.9.0
+PyJWT==2.8.0
+PyMuPDF==1.24.2
+PyMuPDFb==1.24.1
+pyparsing==3.1.2
+pypdf==4.2.0
+pysbd==0.3.4
+python-dotenv==1.0.0
+python-engineio==4.9.0
+python-graphql-client==0.4.3
+python-json-logger==2.0.7
+python-magic==0.4.27
+python-multipart==0.0.6
+python-socketio==5.11.2
+pytz==2024.1
+PyYAML==6.0.1
+qdrant-client==1.9.1
+qtconsole==5.5.1
+QtPy==2.4.1
+ragas==0.1.7
+referencing==0.34.0
+regex==2024.4.16
+requests==2.31.0
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rich==13.7.1
+rpds-py==0.18.0
+scikit-learn==1.4.2
+scipy==1.13.0
+Send2Trash==1.8.3
+sentry-sdk==1.45.0
+setproctitle==1.3.3
+simple-websocket==1.0.0
+smmap==5.0.1
+sniffio==1.3.1
+soupsieve==2.5
+SQLAlchemy==2.0.29
+starlette==0.27.0
+streamlit==1.33.0
+striprtf==0.0.26
+syncer==2.0.3
+tenacity==8.2.3
+terminado==0.18.1
+threadpoolctl==3.4.0
+tiktoken==0.6.0
+tinycss2==1.2.1
+toml==0.10.2
+tomli==2.0.1
+toolz==0.12.1
+tqdm==4.66.2
+types-python-dateutil==2.9.0.20240316
+types-requests==2.31.0.20240406
+typing-inspect==0.9.0
+tzdata==2024.1
+uptrace==1.24.0
+uri-template==1.3.0
+urllib3==2.2.1
+uvicorn==0.23.2
+wandb==0.16.6
+watchfiles==0.20.0
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.7.0
+websockets==12.0
+widgetsnbextension==4.0.10
+wikipedia==1.4.0
+wrapt==1.16.0
+wsproto==1.2.0
+xxhash==3.4.1
+yarl==1.9.4