app-a4all-agentic-workflow-sprint-2-deploy-docker-live

Dockerfile copy

@@ -0,0 +1,34 @@
+FROM python:3.11.3
+
+# 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
+
+# Get secret OPENAI_API_KEY and clone it as repo at buildtime / changed required to true
+RUN --mount=type=secret,id=OPENAI_API_KEY,mode=0444,required=true
+RUN --mount=type=secret,id=HF_TOKEN,mode=0444,required=true \
+    cat /run/secrets/HF_TOKEN > /home/user/cli_token
+
+RUN pip install -U "huggingface_hub[cli]" 
+RUN git init & git config --global credential.helper store
+RUN huggingface-cli login --token $(cat /home/user/cli_token) --add-to-git-credential
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME
+
+# Clone and run ea4all-agent
+RUN git clone https://avfranco:$(cat cli_token)@huggingface.co/spaces/avfranco/ea4all-agent
+WORKDIR /home/user/ea4all-agent
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+
+CMD ["python","app.py"]

README.md

@@ -1,5 +1,5 @@
 ---
-title: Talk to your IT landscape
+title: Talk to your Multi-Agent Architect
 emoji: 👁
 colorFrom: purple
 colorTo: green
@@ -10,43 +10,78 @@ license: mit
 
 # Title
 
-Empower you with access to the value of Enterprise Architecture Knowledge using my Generative AI abilities.
-        
+Empower people with access to the value of Enterprise Architecture Knowledge using my Generative AI abilities.
 
-# My Name
-
-ea4all-agent-gpt, your Architect to talk about Enterprise landscape using your own language.
 
 ## Overview
 
-What if you could interact with your enterprise architecture landscape using natural language, for example, ask what oppurtinities for simplification it may have. So, you would be able to identify initial options to a new business problem or assess impact of changes. That's not all, you would be able to understand what applications support a business capability or their roadmap, enhance the governance and assurance process to accelerate the solution architecture delivery, improve quality and increase collaboration.
+What if you could interact with your IT landscape using natural language, for example, \
+ask what oppurtinities for simplification it may have. So, you would be able to identify initial options to a new business problem \
+or assess impact of changes. That's not all, you would be able to identify risks and vulnerabilities on your solution architecture visual artefacts and how to mitigate them, \
+enhance the governance and assurance process to accelerate the solution architecture delivery, \
+improve quality and increase collaboration.
+
+## Knowledge context
+
+A synthetic sample IT Landscape dataset, which is described below, is used as context to answer any inquiry for purpose of this minimal-viable release.
 
-## Dataset
+    - Application name
+        - Business fit: appropriate, inadequate, perfect
+        - Technical fit: adequate, insufficient, perfect
+        - Business_criticality: operational, medium, high, critical
+        - Roadmap: maintain, invest, divers
+        - Architect responsible
+        - Hosting: user device, on-premise, IaaS, SaaS
+        - Business capability
+        - Business domain
+        - Description  
+
+Bring Your Own Data: upload your own IT landscape data or Architecture Diagram and start talking to them.
+    
+    - Application Portfolio Management
+        - xlsx tabular format
+        - first row (header) with fields name (colums)
+    
+    - Architecture Visual Artefacts
+        - jpeg, png
 
-Synthetic structured data with following colums: application, business fit, technical fit, business criticality, roadmap, architect, hosting, capability, domain, description
+        **Disclaimer**
+            - Your data & image are not accessible or shared with anyone else nor used for training purpose.
+            - EA4ALL-VQA Agent should be used ONLY FOR Architecture Diagram images.
+            - This feature should NOT BE USED to process inappropriate content.
 
-## Bring you own data
+## Log / Traceability
 
-Upload a xlsx formate file with your own landscape data and start learning more
+For purpose of continuous evolution, questions and answers are logged in. 
 
 ## Architecture
 
-<italic>Core architecture built upon python, langchain, gradio and Openai.<italic>
+<italic>Core architecture built upon python, langchain, meta-faiss, gradio and Openai.<italic>
 
     - Python 3.11.3
         - Pandas
         - Langchain
         - Langsmith
+        - Langgraph
 
     - RAG (Retrieval Augmented Generation)
-        - Vectorstore: Faiss (Facebook AI Similarity Search)
+        - Vectorstore: Faiss (Facebook AI Similarity Search
 
     - Prompt Engineering
-        - Strategy & tactics: Task / Sub-tasks 
+        - Strategy & tactics: Task / Sub-tasks
+        - Agentic-Workflow: Agents
 
-    - Model: OpenAI GPT 3.5-turbo-1106
+    - Models: 
+        - OpenAI GPT 3.5-turbo-1106 (Text Generation)
+        - OpenAI GPT-4-Vision-Preview (Visual Question Answering)
     
-    - Task: tabular-question-answering over your own document
+    - Hierarchical-Agent-Teams: 
+        - Tabular-question-answering over your own document
+        - Supervisor
+        - Visual Questions Answering 
+        - Diagram Component Analysis
+        - Risk & Vulnerability and Mitigation options
+        - Well-Architecture Design Assessment
     
     - User Interface
         - Gradio
@@ -55,10 +90,8 @@ Upload a xlsx formate file with your own landscape data and start learning more
         - CPU basic
         - 2vCPU 16GB RAM
 
-    - Deployment
-        - Docker spaces
 
 ## Agent Architecture
-![Agent System Container](./ea4all/apm_architecture/ea4all_agent_container.png)
+![Agent System Container](images/ea4all_agent_container.png)
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,15 @@
+gradio==4.29.0
+gradio_client==0.16.1
+faiss-cpu==1.7.4
+filetype==1.2.0
+langchain==0.1.16
+langchain-community==0.0.34
+langchain-core==0.1.45
+langchain-openai==0.1.3
+openai==1.10.0
+openpyxl==3.1.2
+pandas==2.2.2
+python-dotenv==1.0.0
+tiktoken==0.5.2
+langgraph==0.0.37
+langsmith==0.1.45