First Commit

.github/workflows/hfspace_cicd.yml

@@ -0,0 +1,20 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push https://haihuynh:[email protected]/spaces/haihuynh/jobs-qa-kg main

.gitignore

@@ -0,0 +1,2 @@
+.venv
+.idea

Dockerfile

@@ -0,0 +1,33 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:latest
+
+RUN apt-get update
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the "user" user
+USER user
+
+# Set home to the user's home directory
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Try and run pip command after setting the user with `USER user` to avoid permission issues with Python
+RUN pip install --no-cache-dir --upgrade pip
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+
+CMD ["python", "main.py"]

README.md

@@ -0,0 +1,7 @@
+---
+title: JobsQA KnowledgeGraph
+sdk: docker
+emoji: 👀
+colorFrom: yellow
+colorTo: indigo
+---

main.py

@@ -0,0 +1,24 @@
+import gradio as gr
+from utils import llm_answer
+
+# demo = gr.ChatInterface(
+#     fn = echo,
+#     multimodal= True,    # Allow upload CV
+#     examples = ["hello", "hola", "merhaba"],
+#     title= "Echo Bot",
+#     description= "Chatbot to answer about job postings & recommend jobs based on your CV.",
+#     theme= None,
+#     autofocus= True,
+#     fill_height= False,
+# )
+
+
+demo = gr.ChatInterface(
+    fn= llm_answer,
+    examples=[],
+    title="Jobs QA & Recommendations Chatbot",
+    multimodal=True,
+)
+
+if __name__ == "__main__":
+    demo.launch(server_name = "0.0.0.0", server_port = 7860)

prompts/cypher_prompt.yaml

@@ -0,0 +1,53 @@
+input_variables: [schema, question]
+output_parser: null
+template: |
+  Task:Generate Cypher statement to query a graph database.
+  Instructions:
+  Use only the provided relationship types and properties in the schema.
+  Do not use any other relationship types or properties that are not provided.
+  Schema:
+  {schema}
+  Note: Do not include any explanations or apologies in your responses.
+  Do not respond to any questions that might ask anything else than for you to construct a Cypher statement.
+  Do not include any text except the generated Cypher statement.
+
+  Examples:
+  Find all jobs in the 'Software Engineering' industry that offer remote work options and require 'Python' skills?
+  MATCH (j:Job)
+  WHERE j.name CONTAINS 'Software Engineer'
+  AND j.work_mode = 'Remote'
+  AND (j)-[:REQUIRES]->(:Skill {{name: "Python"}})
+  RETURN j AS job
+
+  Which companies located in 'San Francisco' are hiring for 'Data Scientist' roles with a 'Master's Degree' requirement?
+  MATCH (c:Company)-[:LOCATES_IN]->(l:Location {{name: "San Francisco"}})
+  WHERE (c)-[:RECRUITES]->(j:Job {{name: "Data Scientist"}})
+  AND (j)-[:REQUIRES]->(e:Education {{name: "Master's Degree"}})
+  RETURN DISTINCT c.name AS company
+
+  What are the most common skills required for 'Product Manager' jobs across different industries?
+  MATCH (j:Job {{name: "Product Manager"}})-[:REQUIRES]->(s:Skill)
+  RETURN s.name, count(*) AS skill_count
+  ORDER BY skill_count DESC
+  LIMIT 10
+
+  Find all jobs that require at least 5 years of experience and a 'Bachelor's Degree' in 'Computer Science':
+  MATCH (j:Job)-[:REQUIRES]->(e:Education {{name: "Bachelor's Degree", fields: "Computer Science"}})
+  WHERE (j)-[:REQUIRES]->(we:Work_Exper {{duration: "5 years"}})
+  RETURN j AS job
+
+  Identify companies that are subsidiaries of 'Google' and are recruiting for 'Software Engineer' roles with 'Senior' level.
+  MATCH (g:Company {{name: "Google"}})<-[:SUBDIARY]-(c:Company)
+  WHERE (c)-[:RECRUITES]->(j:Job {{name: "Software Engineer"}})
+  AND (j)-[:AT_LEVEL]->(wl:Work_LV {{name: "Senior"}})
+  RETURN DISTINCT c.name AS company
+
+  Find companies recruiting "Machine Learning" jobs and their corresponding job titles.
+  MATCH (company: Company)-[:RECRUITES]->(job: Job)
+  WHERE job.name CONTAINS "Machine Learning"
+  RETURN company.name as company_name, job.name as job_title
+
+  The question is:
+  {question}
+
+template_format: f-string

prompts/qa_prompt.yaml

@@ -0,0 +1,20 @@
+input_variables: [context, question]
+output_parser: null
+template: |
+  Task: answer the question you are given based on the context provided.
+  Instructions:
+  You are an assistant that helps to form nice and human understandable answers.
+  Use the context information provided to generate a well organized and comprehensive answer to the user's question.
+  When the provided information contains multiple elements, structure your answer as a bulleted or numbered list to enhance clarity and readability.
+  You must use the information to construct your answer.
+  The provided information is authoritative; do not doubt it or try to use your internal knowledge to correct it.
+  Make the answer sound like a response to the question without mentioning that you based the result on the given information.
+  If there is no information provided, say that the knowledge base returned empty results.
+  You should answer result in Vietnamese.
+
+  Here's the information:
+  {context}
+
+  Question: {question}
+  Answer:
+template_format: f-string

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+langchain
+langchain-community
+langchain-google-genai
+neo4j

utils.py

@@ -0,0 +1,76 @@
+import os
+import yaml
+from dotenv import load_dotenv
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_community.graphs import Neo4jGraph
+from langchain_core.prompts.prompt import PromptTemplate
+from langchain.chains import GraphCypherQAChain
+from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
+
+def config():
+    # load_dotenv()
+
+    # Set up Neo4J & Gemini API
+    os.environ["NEO4J_URI"] = os.getenv("NEO4J_URI")
+    os.environ["NEO4J_USERNAME"] = os.getenv("NEO4J_USERNAME")
+    os.environ["NEO4J_PASSWORD"] = os.getenv("NEO4J_PASSWORD")
+    os.environ["GOOGLE_API_KEY"] = os.getenv("GEMINI_API_KEY")
+
+def load_prompt(filepath):
+    with open(filepath, "r") as file:
+        prompt = yaml.safe_load(file)
+
+    return prompt
+
+def init_():
+    config()
+    knowledge_graph = Neo4jGraph()
+    llm_chat = ChatGoogleGenerativeAI(
+        model= "gemini-1.5-flash-latest"
+    )
+
+    # Connect to Neo4J Knowledge Graph
+    cypher_prompt = load_prompt("hf_space/prompts/cypher_prompt.yaml")
+    qa_prompt = load_prompt("hf_space/prompts/qa_prompt.yaml")
+
+    CYPHER_GENERATION_PROMPT = PromptTemplate(**cypher_prompt)
+    QA_GENERATION_PROMPT = PromptTemplate(**qa_prompt)
+
+    chain = GraphCypherQAChain.from_llm(
+        llm_chat, graph=knowledge_graph, verbose=True,
+        cypher_prompt= CYPHER_GENERATION_PROMPT,
+        qa_prompt= QA_GENERATION_PROMPT
+    )
+    
+    return chain
+
+# Init GraphQA Chain     
+chain = init_()
+
+def get_llm_response(query):
+    return chain.invoke({"query": query})["result"]
+    
+
+def llm_answer(message, history):
+    # history_langchain_format = []
+    #
+    # for human, ai in history:
+    #     history_langchain_format.append(HumanMessage(content= human))
+    #     history_langchain_format.append(AIMessage(content= ai))
+    #
+    # history_langchain_format.append(HumanMessage(content= message["text"]))
+
+    try:
+        response = get_llm_response(message["text"])
+    except Exception:
+        response = "Exception"
+    except Error:
+        response = "Error"
+    return response
+
+# if __name__ == "__main__":
+#     message = "Have any company recruiting jobs about Machine Learning and coresponding job titles?"
+#     history = [("What's your name?", "My name is Gemini")]
+#     resp = llm_answer(message, history)
+#     print(resp)
+