initial

.gitignore

@@ -0,0 +1,4 @@
+__pycache__/
+app-data/
+redis-data/
+k8s/

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.9-slim
+
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+
+RUN export PYTHONUNBUFFERED=1
+
+WORKDIR /app
+COPY app /app
+
+
+EXPOSE 7860
+
+CMD ["python", "-u", "app.py"]

README copy.md

@@ -0,0 +1,93 @@
+# de.rwth.dbis.courserecsys
+
+
+
+## Getting started
+
+To make it easy for you to get started with GitLab, here's a list of recommended next steps.
+
+Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
+
+## Add your files
+
+- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
+- [ ] [Add files using the command line](https://docs.gitlab.com/ee/gitlab-basics/add-file.html#add-a-file-using-the-command-line) or push an existing Git repository with the following command:
+
+```
+cd existing_repo
+git remote add origin https://gitlab.com/myedulife/de.rwth.dbis.courserecsys.git
+git branch -M main
+git push -uf origin main
+```
+
+## Integrate with your tools
+
+- [ ] [Set up project integrations](https://gitlab.com/myedulife/de.rwth.dbis.courserecsys/-/settings/integrations)
+
+## Collaborate with your team
+
+- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
+- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
+- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
+- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
+- [ ] [Set auto-merge](https://docs.gitlab.com/ee/user/project/merge_requests/merge_when_pipeline_succeeds.html)
+
+## Test and Deploy
+
+Use the built-in continuous integration in GitLab.
+
+- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/index.html)
+- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing (SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
+- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
+- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
+- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
+
+***
+
+# Editing this README
+
+When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thanks to [makeareadme.com](https://www.makeareadme.com/) for this template.
+
+## Suggestions for a good README
+
+Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
+
+## Name
+Choose a self-explaining name for your project.
+
+## Description
+Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
+
+## Badges
+On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
+
+## Visuals
+Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
+
+## Installation
+Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
+
+## Usage
+Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
+
+## Support
+Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
+
+## Roadmap
+If you have ideas for releases in the future, it is a good idea to list them in the README.
+
+## Contributing
+State if you are open to contributions and what your requirements are for accepting them.
+
+For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
+
+You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
+
+## Authors and acknowledgment
+Show your appreciation to those who have contributed to the project.
+
+## License
+For open source projects, say how it is licensed.
+
+## Project status
+If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.

app/app.py

@@ -0,0 +1,196 @@
+import gradio as gr
+import pandas as pd
+import redis
+import json
+import requests
+from config import *
+from embedding_setup import retriever, find_similar_occupation
+from data_process import build_skill_query, get_occupations_from_csv, get_courses_from_BA, get_occupation_detial, build_occupation_query
+
+r = redis.Redis(host=REDIS_HOST, port=REDIS_PORT, db=REDIS_DB, decode_responses=True)
+skill_details_mapping = {}
+
+
+# Function to retrieve documents based on selected skills
+def retrieve_documents(occupation,skills):
+    output = []
+    output.append(f"<div style=\"text-align: center; font-size: 24px;\">Empfehlungsergebnisse:</div>")
+    oc_uri = occupations.get(occupation, "")
+    skill_query = ''
+    if isinstance(oc_uri, int):
+        df = pd.read_csv("/app/data/berufe_info.csv")
+        target_occupation = df[df['id'] == oc_uri]
+        target_occupation_query = target_occupation['short name'] + ' ' + target_occupation['description']
+        target_occupation_query = target_occupation_query.values[0]
+    else:
+        target_occupation = get_occupation_detial(oc_uri)
+        target_occupation_query = build_occupation_query(target_occupation)
+    for german_label in skills:
+        skill_query += german_label + ' '
+    query = target_occupation_query + ' ' + skill_query
+    print(query)
+    docs = retriever.get_relevant_documents(query)
+    output.append(f"<b>Qualifikationslücke:</b> {skill_query}")
+    output.append(f"<b>Empfohlene Kurse:</b>")
+    for doc in docs:
+        doc_name = doc.metadata.get('name', 'Unnamed Document')
+        doc_url = doc.metadata.get('url', '#')
+        output.append(f"<a href='{doc_url}' target='_blank'>{doc_name}</a>") 
+    output.append(f"<br>")
+    return "<br>".join(output)
+
+
+def get_candidate_courses(occupation, skills):
+    output = []
+    output.append(f"<div style=\"text-align: center; font-size: 24px;\">Empfehlungsergebnisse:</div>")
+    df_lookup = pd.read_csv('/app/data/kldb_isco_lookup.csv')
+    df_berufe = pd.read_csv('/app/data/berufe_info.csv')
+    occupation_codes = set()
+    kldB_set = set()
+    occupation_hrefs = set()
+    BA_berufe = set()
+    oc_uri = occupations.get(occupation, "")
+    target_occupation = get_occupation_detial(oc_uri)
+    target_occupation_query = build_occupation_query(target_occupation)
+    
+    for german_label in skills:
+        skill = skill_details_mapping.get(german_label, {})
+        uri = f'https://ec.europa.eu/esco/api/resource/skill?selectedVersion=v1.0.9&language=en&uri={skill["uri"]}'
+        try:
+            skill_response = requests.get(uri)
+            skill_response.raise_for_status()
+            skill_json = skill_response.json()
+            
+            # Combine essential and optional occupations
+            skill_related_occupations = (skill_json['_links'].get('isEssentialForOccupation', []) +
+                                          skill_json['_links'].get('isOptionalForOccupation', []))
+            
+            for occupation in skill_related_occupations:
+                href = occupation.get('href')
+                if href:
+                    occupation_hrefs.add(href)
+        except requests.RequestException as e:
+            print(f"Error while fetching skill details: {e}")
+                
+    for href in occupation_hrefs:
+        try:
+            occupation_response = requests.get(href)
+            occupation_response.raise_for_status()
+            occupation_details = occupation_response.json()
+            
+            code = occupation_details.get('code')
+            if code:
+                occupation_codes.add(code.split('.')[0])
+        except requests.RequestException as e:
+            print(f"Error while fetching occupation details: {e}")
+            
+    for isco_code in occupation_codes:
+        kldB_codes = df_lookup[df_lookup['isco08'] == int(isco_code)]['kldb2010'].values
+        for code in kldB_codes:
+            kldB_set.add(str(code))
+    dfs = []
+    for kldb in kldB_set:
+        berufe = df_berufe[df_berufe['KldB codes']=='B '+kldb]
+        dfs.append(berufe)
+
+    merged_df = pd.concat(dfs, ignore_index=True)  
+    top_k_berufe = find_similar_occupation(target_occupation_query,merged_df,5,'cosine')
+    for beruf in top_k_berufe:
+        entry_requirement = beruf.metadata['entry_requirements']
+        corrected_json_string = entry_requirement.replace("'", '"')
+        entry_requirement_json = json.loads(corrected_json_string)
+        for js in entry_requirement_json:
+            BA_berufe.add(str(js['data_idref']))
+                
+    result = get_courses_from_BA(BA_berufe)
+    courses = result
+    for course in courses['_embedded']['termine']:
+        output.append(f"<a href='{course['angebot']['link']}' target='_blank'>{course['angebot']['titel']}</a>") 
+
+    return "<br>".join(output)
+
+
+def get_occupation_skills(oc_uri):
+    skills_json = r.get(oc_uri)
+    skill_labels = []
+    if skills_json:
+        skills = json.loads(skills_json)
+        for skill in skills:
+            german_label = skill['preferredLabel']['de']
+            skill_details_mapping[german_label] = skill
+            skill_labels.append(german_label)
+        return skill_labels
+    else:
+        return skill_labels
+    
+def get_occupation_skills_BA(oc_uri):
+    df = pd.read_csv("/app/data/berufe_info.csv")
+    essential_skills = df[df['id'] == oc_uri]['essential skills'].values
+    optional_skills = df[df['id'] == oc_uri]['optional skills'].values
+    combined_skills = essential_skills[0][:-1] + ',' + optional_skills[0][1:]
+    combined_skills = combined_skills.replace("'", "\"")
+    skills = json.loads(combined_skills)
+    skill_labels = []
+    for skill in skills:
+        german_label = skill['skill']
+        skill_details_mapping[german_label] = skill
+        skill_labels.append(german_label)
+    return skill_labels
+
+# Function to update the skills dropdown
+def update_skills(occupation):
+    oc_uri = occupations.get(occupation, "")
+    if isinstance(oc_uri, int):
+        skills = get_occupation_skills_BA(oc_uri)
+        return gr.Dropdown(skills,label="aktuelle Fähigkeiten", multiselect=True,info='Bitte wählen Sie die Fähigkeiten aus, die Sie derzeit besitzen')
+    else:
+        skills = get_occupation_skills(oc_uri)
+        return gr.Dropdown(skills,label="aktuelle Fähigkeiten", multiselect=True,info='Bitte wählen Sie die Fähigkeiten aus, die Sie derzeit besitzen')
+    return 
+
+def update_skillgap(occupation, current_skills):
+    oc_uri = occupations.get(occupation, "")
+    if isinstance(oc_uri, int):
+        ocupation_skills = get_occupation_skills_BA(oc_uri)
+    else:
+        ocupation_skills = get_occupation_skills(oc_uri)
+    skill_gap = [skill for skill in ocupation_skills if skill not in current_skills]
+    
+    return gr.Dropdown(skill_gap, label="Qualifikationslücke", multiselect=True, info='Bitte wählen Sie die Fähigkeiten aus, die Sie lernen möchten.')
+
+if __name__ == "__main__":
+    # Load occupations from CSV
+    occupations_esco = get_occupations_from_csv(CSV_FILE_PATH)
+    df = pd.read_csv("/app/data/berufe_info.csv")
+    occupations_BA = df[['short name', 'id']].set_index('short name').to_dict()['id']
+    occupations = {**occupations_esco, **occupations_BA}
+    # Gradio interface
+    with gr.Blocks(title="MyEduLife Kursempfehlungssystem") as demo:
+        with gr.Row():
+            with gr.Column():
+                occupation_dropdown = gr.Dropdown(list(occupations.keys()), label="Berufe",info='Bitte wählen Sie Ihren Zielberuf aus.')
+                currentskill_dropdown = gr.Dropdown([],label="current skills", multiselect=True,info='Please choose the skills you current have')
+                sb_btn = gr.Button("Submit")
+                skillgap_dropdown = gr.Dropdown([],label="Fähigkeiten", multiselect=True,info='Bitte wählen Sie die Fähigkeiten aus, die Sie lernen möchten.')
+                # Use gr.HTML to display the HTML content
+                button = gr.Button("Kursempfehlungen")
+            with gr.Column():
+                documents_output = gr.HTML()
+
+        occupation_dropdown.change(update_skills, inputs=occupation_dropdown, outputs=currentskill_dropdown)
+
+        sb_btn.click(
+                    update_skillgap, 
+                    inputs=[occupation_dropdown,currentskill_dropdown], 
+                    outputs=skillgap_dropdown
+                )
+
+        button.click(
+                    retrieve_documents, 
+                    inputs=[occupation_dropdown,skillgap_dropdown],
+                    outputs=documents_output
+                    )
+    print('Initialization completed')
+    demo.launch(server_name="0.0.0.0", server_port=7860)
+    
+    

app/config.py

@@ -0,0 +1,19 @@
+import os
+
+# Redis configuration
+REDIS_HOST = os.getenv('REDIS_HOST', 'redis')
+REDIS_PORT = int(os.getenv('REDIS_PORT', 6379))  
+REDIS_DB = int(os.getenv('REDIS_DB', 0))
+
+# Model and embedding configuration
+MODEL_NAME = os.getenv('MODEL_NAME', "intfloat/multilingual-e5-large-instruct")
+ENCODE_KWARGS = {
+    'normalize_embeddings': os.getenv('NORMALIZE_EMBEDDINGS', 'True') == 'True',  
+    'convert_to_tensor': os.getenv('CONVERT_TO_TENSOR', 'True') == 'True'
+}
+QUERY_INSTRUCTION = os.getenv('QUERY_INSTRUCTION', '')
+
+# Other configurations
+TOP_K = int(os.getenv('TOP_K', 5))
+PERSIST_DIRECTORY = os.getenv('PERSIST_DIRECTORY', "/app/data/course_emb_db")
+CSV_FILE_PATH = os.getenv('CSV_FILE_PATH', '/app/data/occupations_de.csv')

app/data_process.py

@@ -0,0 +1,119 @@
+from config import *
+import pandas as pd
+import requests
+
+
+
+
+def build_skill_query(skill):
+    skill_query =  skill['preferredLabel']['de'] +" " + skill['preferredLabel']['en']+" "+ skill['description']['de']+ " "+ skill['description']['en']
+    if skill['borderConcept']['broaderHierarchyConcept']:
+        broader_hierarchy_concept_str = ", ".join(skill['borderConcept']['broaderHierarchyConcept'])
+        skill_query += " " + broader_hierarchy_concept_str
+    else:
+        pass
+    if skill['borderConcept']['broaderSkill']:
+        broaderSkill_str = ", ".join(skill['borderConcept']['broaderSkill'])
+        skill_query += " " + broaderSkill_str
+    else:
+        pass
+    if skill['alternativeLabel']['de']:
+        alternativeLabel_de_str = ", ".join(skill['alternativeLabel']['de'])
+        skill_query += " " + alternativeLabel_de_str
+    else:
+        pass
+    if skill['alternativeLabel']['en']:
+        alternativeLabel_en_str = ", ".join(skill['alternativeLabel']['en'])
+        skill_query += " " + alternativeLabel_en_str
+    else:
+        pass 
+    return skill_query
+
+
+
+def build_occupation_query(occupation):
+    occupation_query = occupation['preferredLabel'].get('de','') +" " + occupation['preferredLabel'].get('en','')+" "+ occupation['description'].get('de','').get('literal','') + " "+ occupation['description'].get('en','').get('literal','')
+    if occupation['_links']['broaderIscoGroup']:
+        for group in occupation['_links']['broaderIscoGroup']:
+            occupation_query += " " + group['title']
+    else:
+        pass
+    return occupation_query      
+
+# Get occupations from a CSV
+def get_occupations_from_csv(file_path):
+    df = pd.read_csv(file_path)
+    return df[['preferredLabel', 'conceptUri']].set_index('preferredLabel').to_dict()['conceptUri']
+
+
+def get_oauth_token():
+    # API endpoint URL
+    token_url = "https://rest.arbeitsagentur.de/oauth/gettoken_cc"
+    
+    # Client credentials
+    client_id = "38053956-6618-4953-b670-b4ae7a2360b1"
+    client_secret = "c385073c-3b97-42a9-b916-08fd8a5d1795"
+    grant_type = "client_credentials"
+    
+    # Prepare request data
+    payload = {
+        "client_id": client_id,
+        "client_secret": client_secret,
+        "grant_type": grant_type
+    }
+    
+    # Send request and get response
+    response = requests.post(token_url, data=payload)
+    
+    # Check if the request was successful
+    if response.status_code == 200:
+        return response.json().get("access_token")
+    else:
+        print("Token request failed:", response.text)
+        return None
+
+def query_weiterbildungssuche_api(token, params):
+    # Set API URL
+    api_url = "https://rest.arbeitsagentur.de/infosysbub/wbsuche/pc/v2/bildungsangebot"
+    
+    # Prepare request headers
+    headers = {
+        "Authorization": f"Bearer {token}"
+    }
+    
+    # Send GET request
+    response = requests.get(api_url, headers=headers, params=params)
+    
+    if response.status_code == 200:
+        return response.json()
+    else:
+        print("API request failed:", response.text)
+        return None
+
+def get_courses_from_BA(ids):
+    # Get OAuth token
+    token = get_oauth_token()
+    if token:
+        # Set query parameters
+        params = {
+            "ids": list(ids)
+        }
+        # Use token to query the API
+        result = query_weiterbildungssuche_api(token, params)
+        return result
+
+
+def get_occupation_detial(oc_uri):
+    uri = f'https://ec.europa.eu/esco/api/resource/occupation?selectedVersion=v1.0.9&language=en&uri={oc_uri}'
+    try:
+            occupation_response = requests.get(uri)
+            occupation_response.raise_for_status()
+            occupation_json = occupation_response.json()
+            return occupation_json
+            
+    except requests.RequestException as e:
+        print(f"Error while fetching skill details: {e}")
+
+
+
+

app/embedding_setup.py

@@ -0,0 +1,49 @@
+from langchain_community.vectorstores import Chroma
+from langchain_community.embeddings import HuggingFaceBgeEmbeddings
+from sentence_transformers import SentenceTransformer, util
+from langchain.docstore.document import Document
+import numpy as np
+from config import *
+import os
+
+os.environ['CURL_CA_BUNDLE'] = ""
+embedding_int = HuggingFaceBgeEmbeddings(
+    model_name=MODEL_NAME,
+    encode_kwargs=ENCODE_KWARGS,
+    query_instruction=QUERY_INSTRUCTION
+)
+
+embedding_sim = HuggingFaceBgeEmbeddings(
+    model_name=MODEL_NAME,
+    encode_kwargs=ENCODE_KWARGS,
+    query_instruction='Retrieve semantically similar text.'
+)
+
+db = Chroma(persist_directory=PERSIST_DIRECTORY, embedding_function=embedding_int)
+retriever = db.as_retriever(search_kwargs={"k": TOP_K})
+
+
+def find_similar_occupation(target_occupation_query, berufe, top_k, similarity_func):
+  
+    # Pro kurs wird ein Document erstellt. Dieses enthält Metadaten sowie einen page_content. 
+    # Der Inhalt von page_content wird embedded und so für die sucher verwendet.
+    docs = []
+    for index, beruf in berufe.iterrows():  
+        # Create document.
+        doc = Document(
+            page_content= beruf['short name'] + ' ' + beruf['full name'] + ' ' + beruf['description'],  
+            metadata={
+                "id": beruf["id"],
+                "name": beruf['short name'],
+                "description": beruf["description"],
+                "entry_requirements": beruf["entry requirements"]
+            },
+        )
+        docs.append(doc)
+    
+    db_temp = Chroma.from_documents(documents = docs, embedding= embedding_sim, collection_metadata = {"hnsw:space": similarity_func})
+    # Retriever will search for the top_5 most similar documents to the query.
+    retriever_temp = db_temp.as_retriever(search_kwargs={"k": top_k})
+    top_similar_occupations = retriever_temp.get_relevant_documents(target_occupation_query)
+
+    return top_similar_occupations

docker-compose.yml

@@ -0,0 +1,31 @@
+version: '3.8'
+
+services:
+  webapp:
+    image: escoai
+    ports:
+      - "7860:7860"
+    volumes:
+      - ./app-data:/app/data
+    depends_on:
+      - redis
+    environment:
+      REDIS_HOST: redis
+      REDIS_PORT: 6379
+      REDIS_DB: 0
+      MODEL_NAME: "/app/data/multilingual-e5-large-instruct"
+      NORMALIZE_EMBEDDINGS: "True"
+      CONVERT_TO_TENSOR: "True"
+      QUERY_INSTRUCTION: "Given a skill, retrieve relevant courses that teach the skill: "
+      TOP_K: 5
+      PERSIST_DIRECTORY: "/app/data/course_emb_db"
+      CSV_FILE_PATH: "/app/data/occupations_de.csv"
+
+  redis:
+    image: "redis:latest"
+    volumes:
+      - ./redis-data:/data
+
+
+volumes:
+  redis-data: