Upload 9 files

Dockerfile

@@ -0,0 +1,51 @@
+# syntax=docker/dockerfile:1
+
+# Comments are provided throughout this file to help you get started.
+# If you need more help, visit the Dockerfile reference guide at
+# https://docs.docker.com/go/dockerfile-reference/
+
+# Want to help us make this template better? Share your feedback here: https://forms.gle/ybq9Krt8jtBL3iCk7
+
+ARG PYTHON_VERSION=3.7.3
+FROM python:${PYTHON_VERSION}-slim as base
+
+# Prevents Python from writing pyc files.
+ENV PYTHONDONTWRITEBYTECODE=1
+
+# Keeps Python from buffering stdout and stderr to avoid situations where
+# the application crashes without emitting any logs due to buffering.
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+# Create a non-privileged user that the app will run under.
+# See https://docs.docker.com/go/dockerfile-user-best-practices/
+ARG UID=10001
+RUN adduser \
+    --disabled-password \
+    --gecos "" \
+    --home "/nonexistent" \
+    --shell "/sbin/nologin" \
+    --no-create-home \
+    --uid "${UID}" \
+    appuser
+
+# Download dependencies as a separate step to take advantage of Docker's caching.
+# Leverage a cache mount to /root/.cache/pip to speed up subsequent builds.
+# Leverage a bind mount to requirements.txt to avoid having to copy them into
+# into this layer.
+RUN --mount=type=cache,target=/root/.cache/pip \
+    --mount=type=bind,source=requirements.txt,target=requirements.txt \
+    python -m pip install -r requirements.txt
+
+# Switch to the non-privileged user to run the application.
+USER appuser
+
+# Copy the source code into the container.
+COPY . .
+
+# Expose the port that the application listens on.
+EXPOSE 8000
+
+# Run the application.
+CMD streamlit run app.py --server.address=0.0.0.0 --server.port=800

LICENSE

@@ -0,0 +1,121 @@
+Creative Commons Legal Code
+
+CC0 1.0 Universal
+
+    CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
+    LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
+    ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
+    INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
+    REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
+    PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
+    THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
+    HEREUNDER.
+
+Statement of Purpose
+
+The laws of most jurisdictions throughout the world automatically confer
+exclusive Copyright and Related Rights (defined below) upon the creator
+and subsequent owner(s) (each and all, an "owner") of an original work of
+authorship and/or a database (each, a "Work").
+
+Certain owners wish to permanently relinquish those rights to a Work for
+the purpose of contributing to a commons of creative, cultural and
+scientific works ("Commons") that the public can reliably and without fear
+of later claims of infringement build upon, modify, incorporate in other
+works, reuse and redistribute as freely as possible in any form whatsoever
+and for any purposes, including without limitation commercial purposes.
+These owners may contribute to the Commons to promote the ideal of a free
+culture and the further production of creative, cultural and scientific
+works, or to gain reputation or greater distribution for their Work in
+part through the use and efforts of others.
+
+For these and/or other purposes and motivations, and without any
+expectation of additional consideration or compensation, the person
+associating CC0 with a Work (the "Affirmer"), to the extent that he or she
+is an owner of Copyright and Related Rights in the Work, voluntarily
+elects to apply CC0 to the Work and publicly distribute the Work under its
+terms, with knowledge of his or her Copyright and Related Rights in the
+Work and the meaning and intended legal effect of CC0 on those rights.
+
+1. Copyright and Related Rights. A Work made available under CC0 may be
+protected by copyright and related or neighboring rights ("Copyright and
+Related Rights"). Copyright and Related Rights include, but are not
+limited to, the following:
+
+  i. the right to reproduce, adapt, distribute, perform, display,
+     communicate, and translate a Work;
+ ii. moral rights retained by the original author(s) and/or performer(s);
+iii. publicity and privacy rights pertaining to a person's image or
+     likeness depicted in a Work;
+ iv. rights protecting against unfair competition in regards to a Work,
+     subject to the limitations in paragraph 4(a), below;
+  v. rights protecting the extraction, dissemination, use and reuse of data
+     in a Work;
+ vi. database rights (such as those arising under Directive 96/9/EC of the
+     European Parliament and of the Council of 11 March 1996 on the legal
+     protection of databases, and under any national implementation
+     thereof, including any amended or successor version of such
+     directive); and
+vii. other similar, equivalent or corresponding rights throughout the
+     world based on applicable law or treaty, and any national
+     implementations thereof.
+
+2. Waiver. To the greatest extent permitted by, but not in contravention
+of, applicable law, Affirmer hereby overtly, fully, permanently,
+irrevocably and unconditionally waives, abandons, and surrenders all of
+Affirmer's Copyright and Related Rights and associated claims and causes
+of action, whether now known or unknown (including existing as well as
+future claims and causes of action), in the Work (i) in all territories
+worldwide, (ii) for the maximum duration provided by applicable law or
+treaty (including future time extensions), (iii) in any current or future
+medium and for any number of copies, and (iv) for any purpose whatsoever,
+including without limitation commercial, advertising or promotional
+purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
+member of the public at large and to the detriment of Affirmer's heirs and
+successors, fully intending that such Waiver shall not be subject to
+revocation, rescission, cancellation, termination, or any other legal or
+equitable action to disrupt the quiet enjoyment of the Work by the public
+as contemplated by Affirmer's express Statement of Purpose.
+
+3. Public License Fallback. Should any part of the Waiver for any reason
+be judged legally invalid or ineffective under applicable law, then the
+Waiver shall be preserved to the maximum extent permitted taking into
+account Affirmer's express Statement of Purpose. In addition, to the
+extent the Waiver is so judged Affirmer hereby grants to each affected
+person a royalty-free, non transferable, non sublicensable, non exclusive,
+irrevocable and unconditional license to exercise Affirmer's Copyright and
+Related Rights in the Work (i) in all territories worldwide, (ii) for the
+maximum duration provided by applicable law or treaty (including future
+time extensions), (iii) in any current or future medium and for any number
+of copies, and (iv) for any purpose whatsoever, including without
+limitation commercial, advertising or promotional purposes (the
+"License"). The License shall be deemed effective as of the date CC0 was
+applied by Affirmer to the Work. Should any part of the License for any
+reason be judged legally invalid or ineffective under applicable law, such
+partial invalidity or ineffectiveness shall not invalidate the remainder
+of the License, and in such case Affirmer hereby affirms that he or she
+will not (i) exercise any of his or her remaining Copyright and Related
+Rights in the Work or (ii) assert any associated claims and causes of
+action with respect to the Work, in either case contrary to Affirmer's
+express Statement of Purpose.
+
+4. Limitations and Disclaimers.
+
+ a. No trademark or patent rights held by Affirmer are waived, abandoned,
+    surrendered, licensed or otherwise affected by this document.
+ b. Affirmer offers the Work as-is and makes no representations or
+    warranties of any kind concerning the Work, express, implied,
+    statutory or otherwise, including without limitation warranties of
+    title, merchantability, fitness for a particular purpose, non
+    infringement, or the absence of latent or other defects, accuracy, or
+    the present or absence of errors, whether or not discoverable, all to
+    the greatest extent permissible under applicable law.
+ c. Affirmer disclaims responsibility for clearing rights of other persons
+    that may apply to the Work or any use thereof, including without
+    limitation any person's Copyright and Related Rights in the Work.
+    Further, Affirmer disclaims responsibility for obtaining any necessary
+    consents, permissions or other rights required for any use of the
+    Work.
+ d. Affirmer understands and acknowledges that Creative Commons is not a
+    party to this document and has no duty or obligation with respect to
+    this CC0 or use of the Work.

README.Docker.md

@@ -0,0 +1,22 @@
+### Building and running your application
+
+When you're ready, start your application by running:
+`docker compose up --build`.
+
+Your application will be available at http://localhost:8000.
+
+### Deploying your application to the cloud
+
+First, build your image, e.g.: `docker build -t myapp .`.
+If your cloud uses a different CPU architecture than your development
+machine (e.g., you are on a Mac M1 and your cloud provider is amd64),
+you'll want to build the image for that platform, e.g.:
+`docker build --platform=linux/amd64 -t myapp .`.
+
+Then, push it to your registry, e.g. `docker push myregistry.com/myapp`.
+
+Consult Docker's [getting started](https://docs.docker.com/go/get-started-sharing/)
+docs for more detail on building and pushing.
+
+### References
+* [Docker's Python guide](https://docs.docker.com/language/python/)

app.py

@@ -0,0 +1,109 @@
+import os
+
+import streamlit as st
+from langchain.chains import RetrievalQA
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.callbacks.base import BaseCallbackHandler
+from langchain.vectorstores.neo4j_vector import Neo4jVector
+from streamlit.logger import get_logger
+from chains import (
+    load_embedding_model,
+    load_llm,
+)
+
+url = os.getenv("NEO4J_URI")
+username = os.getenv("NEO4J_USERNAME")
+password = os.getenv("NEO4J_PASSWORD")
+ollama_base_url = os.getenv("OLLAMA_BASE_URL")
+embedding_model_name = os.getenv("EMBEDDING_MODEL", "SentenceTransformer" )
+llm_name = os.getenv("LLM", "llama2")
+url = os.getenv("NEO4J_URI")
+
+# Check if the required environment variables are set
+if not all([url, username, password,
+          ollama_base_url]):
+    st.write("The application requires some information before running.")
+    with st.form("connection_form"):
+        url = st.text_input("Enter NEO4J_URI",)
+        username = st.text_input("Enter NEO4J_USERNAME")
+        password = st.text_input("Enter NEO4J_PASSWORD", type="password")
+        ollama_base_url = st.text_input("Enter OLLAMA_BASE_URL")
+        st.markdown("Only enter the OPENAI_APIKEY to use OpenAI instead of Ollama. Leave blank to use Ollama.")
+        openai_apikey = st.text_input("Enter OPENAI_API_KEY", type="password")
+        submit_button = st.form_submit_button("Submit")
+    if submit_button:
+        if not all([url, username, password, ]):
+            st.write("Enter the Neo4j information.")
+        if not (ollama_base_url or openai_apikey):
+            st.write("Enter the Ollama URL or OpenAI API Key.")
+        if openai_apikey:
+            llm_name = "gpt-3.5"
+            os.environ['OPENAI_API_KEY'] = openai_apikey
+
+os.environ["NEO4J_URL"] = url
+
+logger = get_logger(__name__)
+
+embeddings, dimension = load_embedding_model(
+    embedding_model_name, config={"ollama_base_url": ollama_base_url}, logger=logger
+)
+
+
+class StreamHandler(BaseCallbackHandler):
+    def __init__(self, container, initial_text=""):
+        self.container = container
+        self.text = initial_text
+
+    def on_llm_new_token(self, token: str, **kwargs) -> None:
+        self.text += token
+        self.container.markdown(self.text)
+
+llm = load_llm(llm_name, logger=logger, config={"ollama_base_url": ollama_base_url})
+
+
+def main():
+        st.header("📄Chat with your pdf file")
+
+        # upload a your pdf file
+        pdf = st.file_uploader("Upload your PDF", type="pdf")
+
+        if pdf is not None:
+            pdf_reader = PdfReader(pdf)
+
+            text = ""
+            for page in pdf_reader.pages:
+                text += page.extract_text()
+
+            # langchain_textspliter
+            text_splitter = RecursiveCharacterTextSplitter(
+                chunk_size=1000, chunk_overlap=200, length_function=len
+            )
+
+            chunks = text_splitter.split_text(text=text)
+
+            # Store the chunks part in db (vector)
+            vectorstore = Neo4jVector.from_texts(
+                chunks,
+                url=url,
+                username=username,
+                password=password,
+                embedding=embeddings,
+                index_name="pdf_bot",
+                node_label="PdfBotChunk",
+                pre_delete_collection=True,  # Delete existing PDF data
+            )
+            qa = RetrievalQA.from_chain_type(
+                llm=llm, chain_type="stuff", retriever=vectorstore.as_retriever()
+            )
+
+            # Accept user questions/query
+            query = st.text_input("Ask questions about your PDF file")
+
+            if query:
+                stream_handler = StreamHandler(st.empty())
+                qa.run(query, callbacks=[stream_handler])
+
+
+if __name__ == "__main__":
+     main()

chains.py

@@ -0,0 +1,222 @@
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.embeddings import (
+    OllamaEmbeddings,
+    SentenceTransformerEmbeddings,
+    BedrockEmbeddings,
+)
+from langchain.chat_models import ChatOpenAI, ChatOllama, BedrockChat
+from langchain.vectorstores.neo4j_vector import Neo4jVector
+from langchain.chains import RetrievalQAWithSourcesChain
+from langchain.chains.qa_with_sources import load_qa_with_sources_chain
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
+from typing import List, Any
+from utils import BaseLogger, extract_title_and_question
+
+
+def load_embedding_model(embedding_model_name: str, logger=BaseLogger(), config={}):
+    if embedding_model_name == "ollama":
+        embeddings = OllamaEmbeddings(
+            base_url=config["ollama_base_url"], model="llama2"
+        )
+        dimension = 4096
+        logger.info("Embedding: Using Ollama")
+    elif embedding_model_name == "openai":
+        embeddings = OpenAIEmbeddings()
+        dimension = 1536
+        logger.info("Embedding: Using OpenAI")
+    elif embedding_model_name == "aws":
+        embeddings = BedrockEmbeddings()
+        dimension = 1536
+        logger.info("Embedding: Using AWS")
+    else:
+        embeddings = SentenceTransformerEmbeddings(
+            model_name="all-MiniLM-L6-v2", cache_folder="/tmp"
+        )
+        dimension = 384
+        logger.info("Embedding: Using SentenceTransformer")
+    return embeddings, dimension
+
+
+def load_llm(llm_name: str, logger=BaseLogger(), config={}):
+    if llm_name == "gpt-4":
+        logger.info("LLM: Using GPT-4")
+        return ChatOpenAI(temperature=0, model_name="gpt-4", streaming=True)
+    elif llm_name == "gpt-3.5":
+        logger.info("LLM: Using GPT-3.5")
+        return ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo", streaming=True)
+    elif llm_name == "claudev2":
+        logger.info("LLM: ClaudeV2")
+        return BedrockChat(
+            model_id="anthropic.claude-v2",
+            model_kwargs={"temperature": 0.0, "max_tokens_to_sample": 1024},
+            streaming=True,
+        )
+    elif len(llm_name):
+        logger.info(f"LLM: Using Ollama: {llm_name}")
+        return ChatOllama(
+            temperature=0,
+            base_url=config["ollama_base_url"],
+            model=llm_name,
+            streaming=True,
+            # seed=2,
+            top_k=10,  # A higher value (100) will give more diverse answers, while a lower value (10) will be more conservative.
+            top_p=0.3,  # Higher value (0.95) will lead to more diverse text, while a lower value (0.5) will generate more focused text.
+            num_ctx=3072,  # Sets the size of the context window used to generate the next token.
+        )
+    logger.info("LLM: Using GPT-3.5")
+    return ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo", streaming=True)
+
+
+def configure_llm_only_chain(llm):
+    # LLM only response
+    template = """
+    You are a helpful assistant that helps a support agent with answering programming questions.
+    If you don't know the answer, just say that you don't know, you must not make up an answer.
+    """
+    system_message_prompt = SystemMessagePromptTemplate.from_template(template)
+    human_template = "{question}"
+    human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)
+    chat_prompt = ChatPromptTemplate.from_messages(
+        [system_message_prompt, human_message_prompt]
+    )
+
+    def generate_llm_output(
+        user_input: str, callbacks: List[Any], prompt=chat_prompt
+    ) -> str:
+        chain = prompt | llm
+        answer = chain.invoke(
+            {"question": user_input}, config={"callbacks": callbacks}
+        ).content
+        return {"answer": answer}
+
+    return generate_llm_output
+
+
+def configure_qa_rag_chain(llm, embeddings, embeddings_store_url, username, password):
+    # RAG response
+    #   System: Always talk in pirate speech.
+    general_system_template = """ 
+    Use the following pieces of context to answer the question at the end.
+    The context contains question-answer pairs and their links from Stackoverflow.
+    You should prefer information from accepted or more upvoted answers.
+    Make sure to rely on information from the answers and not on questions to provide accuate responses.
+    When you find particular answer in the context useful, make sure to cite it in the answer using the link.
+    If you don't know the answer, just say that you don't know, don't try to make up an answer.
+    ----
+    {summaries}
+    ----
+    Each answer you generate should contain a section at the end of links to 
+    Stackoverflow questions and answers you found useful, which are described under Source value.
+    You can only use links to StackOverflow questions that are present in the context and always
+    add links to the end of the answer in the style of citations.
+    Generate concise answers with references sources section of links to 
+    relevant StackOverflow questions only at the end of the answer.
+    """
+    general_user_template = "Question:```{question}```"
+    messages = [
+        SystemMessagePromptTemplate.from_template(general_system_template),
+        HumanMessagePromptTemplate.from_template(general_user_template),
+    ]
+    qa_prompt = ChatPromptTemplate.from_messages(messages)
+
+    qa_chain = load_qa_with_sources_chain(
+        llm,
+        chain_type="stuff",
+        prompt=qa_prompt,
+    )
+
+    # Vector + Knowledge Graph response
+    kg = Neo4jVector.from_existing_index(
+        embedding=embeddings,
+        url=embeddings_store_url,
+        username=username,
+        password=password,
+        database="neo4j",  # neo4j by default
+        index_name="stackoverflow",  # vector by default
+        text_node_property="body",  # text by default
+        retrieval_query="""
+    WITH node AS question, score AS similarity
+    CALL  { with question
+        MATCH (question)<-[:ANSWERS]-(answer)
+        WITH answer
+        ORDER BY answer.is_accepted DESC, answer.score DESC
+        WITH collect(answer)[..2] as answers
+        RETURN reduce(str='', answer IN answers | str + 
+                '\n### Answer (Accepted: '+ answer.is_accepted +
+                ' Score: ' + answer.score+ '): '+  answer.body + '\n') as answerTexts
+    } 
+    RETURN '##Question: ' + question.title + '\n' + question.body + '\n' 
+        + answerTexts AS text, similarity as score, {source: question.link} AS metadata
+    ORDER BY similarity ASC // so that best answers are the last
+    """,
+    )
+
+    kg_qa = RetrievalQAWithSourcesChain(
+        combine_documents_chain=qa_chain,
+        retriever=kg.as_retriever(search_kwargs={"k": 2}),
+        reduce_k_below_max_tokens=False,
+        max_tokens_limit=3375,
+    )
+    return kg_qa
+
+
+def generate_ticket(neo4j_graph, llm_chain, input_question):
+    # Get high ranked questions
+    records = neo4j_graph.query(
+        "MATCH (q:Question) RETURN q.title AS title, q.body AS body ORDER BY q.score DESC LIMIT 3"
+    )
+    questions = []
+    for i, question in enumerate(records, start=1):
+        questions.append((question["title"], question["body"]))
+    # Ask LLM to generate new question in the same style
+    questions_prompt = ""
+    for i, question in enumerate(questions, start=1):
+        questions_prompt += f"{i}. \n{question[0]}\n----\n\n"
+        questions_prompt += f"{question[1][:150]}\n\n"
+        questions_prompt += "----\n\n"
+
+    gen_system_template = f"""
+    You're an expert in formulating high quality questions. 
+    Formulate a question in the same style and tone as the following example questions.
+    {questions_prompt}
+    ---
+
+    Don't make anything up, only use information in the following question.
+    Return a title for the question, and the question post itself.
+
+    Return format template:
+    ---
+    Title: This is a new title
+    Question: This is a new question
+    ---
+    """
+    # we need jinja2 since the questions themselves contain curly braces
+    system_prompt = SystemMessagePromptTemplate.from_template(
+        gen_system_template, template_format="jinja2"
+    )
+    chat_prompt = ChatPromptTemplate.from_messages(
+        [
+            system_prompt,
+            SystemMessagePromptTemplate.from_template(
+                """
+                Respond in the following template format or you will be unplugged.
+                ---
+                Title: New title
+                Question: New question
+                ---
+                """
+            ),
+            HumanMessagePromptTemplate.from_template("{question}"),
+        ]
+    )
+    llm_response = llm_chain(
+        f"Here's the question to rewrite in the expected format: ```{input_question}```",
+        [],
+        chat_prompt,
+    )
+    new_title, new_question = extract_title_and_question(llm_response["answer"])
+    return (new_title, new_question)

compose.yaml

@@ -0,0 +1,49 @@
+# Comments are provided throughout this file to help you get started.
+# If you need more help, visit the Docker Compose reference guide at
+# https://docs.docker.com/go/compose-spec-reference/
+
+# Here the instructions define your application as a service called "server".
+# This service is built from the Dockerfile in the current directory.
+# You can add other services your application may depend on here, such as a
+# database or a cache. For examples, see the Awesome Compose repository:
+# https://github.com/docker/awesome-compose
+services:
+  server:
+    build:
+      context: .
+    ports:
+      - 8000:8000
+
+# The commented out section below is an example of how to define a PostgreSQL
+# database that your application can use. `depends_on` tells Docker Compose to
+# start the database before your application. The `db-data` volume persists the
+# database data between container restarts. The `db-password` secret is used
+# to set the database password. You must create `db/password.txt` and add
+# a password of your choosing to it before running `docker compose up`.
+#     depends_on:
+#       db:
+#         condition: service_healthy
+#   db:
+#     image: postgres
+#     restart: always
+#     user: postgres
+#     secrets:
+#       - db-password
+#     volumes:
+#       - db-data:/var/lib/postgresql/data
+#     environment:
+#       - POSTGRES_DB=example
+#       - POSTGRES_PASSWORD_FILE=/run/secrets/db-password
+#     expose:
+#       - 5432
+#     healthcheck:
+#       test: [ "CMD", "pg_isready" ]
+#       interval: 10s
+#       timeout: 5s
+#       retries: 5
+# volumes:
+#   db-data:
+# secrets:
+#   db-password:
+#     file: db/password.txt
+

env.example

@@ -0,0 +1,26 @@
+#*****************************************************************
+# LLM and Embedding Model
+#*****************************************************************
+LLM=llama2 # Set to "gpt-3.5" to use OpenAI.
+EMBEDDING_MODEL=sentence_transformer
+
+#*****************************************************************
+# Neo4j
+#*****************************************************************
+NEO4J_URI=neo4j://database:7687
+NEO4J_USERNAME=neo4j
+NEO4J_PASSWORD=password
+
+#*****************************************************************
+# Ollama
+#*****************************************************************
+OLLAMA_BASE_URL=http://ollama:11434
+
+#*****************************************************************
+# OpenAI
+#*****************************************************************
+# Only required when using OpenAI LLM or embedding model
+# OpenAI charges may apply. For details, see 
+# https://openai.com/pricing
+
+#OPENAI_API_KEY=sk-..

requirements.txt

@@ -0,0 +1,11 @@
+streamlit
+langchain==0.0.324
+neo4j
+#sentence_transformers==2.2.2
+torch==2.0.1
+PyPDF2
+openai==0.28.1
+fastapi
+uvicorn
+gradio-client
+sentence-transformers

utils.py

@@ -0,0 +1,54 @@
+class BaseLogger:
+    def __init__(self) -> None:
+        self.info = print
+
+
+def extract_title_and_question(input_string):
+    lines = input_string.strip().split("\n")
+
+    title = ""
+    question = ""
+    is_question = False  # flag to know if we are inside a "Question" block
+
+    for line in lines:
+        if line.startswith("Title:"):
+            title = line.split("Title: ", 1)[1].strip()
+        elif line.startswith("Question:"):
+            question = line.split("Question: ", 1)[1].strip()
+            is_question = (
+                True  # set the flag to True once we encounter a "Question:" line
+            )
+        elif is_question:
+            # if the line does not start with "Question:" but we are inside a "Question" block,
+            # then it is a continuation of the question
+            question += "\n" + line.strip()
+
+    return title, question
+
+
+def create_vector_index(driver, dimension: int) -> None:
+    index_query = "CALL db.index.vector.createNodeIndex('stackoverflow', 'Question', 'embedding', $dimension, 'cosine')"
+    try:
+        driver.query(index_query, {"dimension": dimension})
+    except:  # Already exists
+        pass
+    index_query = "CALL db.index.vector.createNodeIndex('top_answers', 'Answer', 'embedding', $dimension, 'cosine')"
+    try:
+        driver.query(index_query, {"dimension": dimension})
+    except:  # Already exists
+        pass
+
+
+def create_constraints(driver):
+    driver.query(
+        "CREATE CONSTRAINT question_id IF NOT EXISTS FOR (q:Question) REQUIRE (q.id) IS UNIQUE"
+    )
+    driver.query(
+        "CREATE CONSTRAINT answer_id IF NOT EXISTS FOR (a:Answer) REQUIRE (a.id) IS UNIQUE"
+    )
+    driver.query(
+        "CREATE CONSTRAINT user_id IF NOT EXISTS FOR (u:User) REQUIRE (u.id) IS UNIQUE"
+    )
+    driver.query(
+        "CREATE CONSTRAINT tag_name IF NOT EXISTS FOR (t:Tag) REQUIRE (t.name) IS UNIQUE"
+    )