avfranco commited on
Commit
8f9e4eb
1 Parent(s): d7f9d0f

app-ea4all-sprint-5-apm-agentic-routing-fallback-self-correction-streaming-deploy-live-docker

Browse files
Files changed (3) hide show
  1. Dockerfile +2 -0
  2. README.md +7 -12
  3. requirements.txt +19 -17
Dockerfile CHANGED
@@ -20,6 +20,8 @@ RUN --mount=type=secret,id=LANGCHAIN_API_KEY,mode=0444,required=true
20
  # HF private spaces token access
21
  RUN --mount=type=secret,id=HUGGINGFACEHUB_API_TOKEN,mode=0444,required=true \
22
  cat /run/secrets/HUGGINGFACEHUB_API_TOKEN > /home/user/cli_token
 
 
23
 
24
  RUN pip install -U "huggingface_hub[cli]"
25
  RUN git init & git config --global credential.helper store
 
20
  # HF private spaces token access
21
  RUN --mount=type=secret,id=HUGGINGFACEHUB_API_TOKEN,mode=0444,required=true \
22
  cat /run/secrets/HUGGINGFACEHUB_API_TOKEN > /home/user/cli_token
23
+ # Azure BING Search AI API
24
+ RUN --mount=type=secret,id=BING_SUBSCRIPTION_KEY,mode=0444,required=true
25
 
26
  RUN pip install -U "huggingface_hub[cli]"
27
  RUN git init & git config --global credential.helper store
README.md CHANGED
@@ -18,9 +18,9 @@ Empower people with ability to harness the value of Enterprise Architecture thro
18
 
19
  `Trigger`: How disruptive may Generative AI be for Enterprise Architecture Capability (People, Process and Tools)? \n
20
  `Motivation`: Master GenAI while disrupting Enterprise Architecture to empower individuals and organisations with ability to harness EA value and make people lives better, safer and more efficient. \n
21
- `Ability`: Exploit my carrer background and skillset across areas such as development, business accumen, innovation and architecture to accelerate GenAI exploration. \n\n
22
 
23
- > That's how the `EA4ALL-Agentic system` was born and ever since continuously evolving as a result of this exploration journey.
24
 
25
  ## Benefits
26
 
@@ -35,7 +35,7 @@ Empower people with ability to harness the value of Enterprise Architecture thro
35
 
36
  ## Knowledge context
37
 
38
- Synthetic datasets are used to exemplify the Agentic System capabilities.
39
 
40
  ### IT Landscape Question and Answering
41
 
@@ -49,11 +49,6 @@ Synthetic datasets are used to exemplify the Agentic System capabilities.
49
  - Business capability
50
  - Business domain
51
  - Description
52
-
53
- - Bring Your Own Data: upload your own IT landscape data
54
- - Application Portfolio Management
55
- - xlsx tabular format
56
- - first row (header) with fields name (colums)
57
 
58
  ### Architecture Diagram Visual Question and Answering
59
 
@@ -96,19 +91,19 @@ Synthetic datasets are used to exemplify the Agentic System capabilities.
96
  - Llama
97
 
98
  - Hierarchical-Agent-Teams:
99
- - Tabular-question-answering over your own document
100
  - Supervisor
101
  - Visual Questions Answering
102
  - Diagram Component Analysis
103
  - Risk & Vulnerability and Mitigation options
104
- - Well-Architecture Design Assessment
105
- - Vision and Target Architecture
106
 
107
  - User Interface
108
  - Gradio
109
 
110
  - Hosting: Huggingface Space
111
-
112
  ## Agentic System Architecture
113
  ![Agent System Container](images/ea4all_agent_container.png)
114
 
 
18
 
19
  `Trigger`: How disruptive may Generative AI be for Enterprise Architecture Capability (People, Process and Tools)? \n
20
  `Motivation`: Master GenAI while disrupting Enterprise Architecture to empower individuals and organisations with ability to harness EA value and make people lives better, safer and more efficient. \n
21
+ `Ability`: Exploit my carrer background and skillset across system development, business accumen, innovation and architecture to accelerate GenAI exploration. \n\n
22
 
23
+ > That's how the `EA4ALL-Agentic system` was born and ever since continuously evolving.
24
 
25
  ## Benefits
26
 
 
35
 
36
  ## Knowledge context
37
 
38
+ Synthetic dataset is used to exemplify the Agentic System capabilities.
39
 
40
  ### IT Landscape Question and Answering
41
 
 
49
  - Business capability
50
  - Business domain
51
  - Description
 
 
 
 
 
52
 
53
  ### Architecture Diagram Visual Question and Answering
54
 
 
91
  - Llama
92
 
93
  - Hierarchical-Agent-Teams:
94
+ - Tabular-question-and-answering
95
  - Supervisor
96
  - Visual Questions Answering
97
  - Diagram Component Analysis
98
  - Risk & Vulnerability and Mitigation options
99
+ - Well-Architected Design Assessment
100
+ - Vision and Target Reference Architecture
101
 
102
  - User Interface
103
  - Gradio
104
 
105
  - Hosting: Huggingface Space
106
+
107
  ## Agentic System Architecture
108
  ![Agent System Container](images/ea4all_agent_container.png)
109
 
requirements.txt CHANGED
@@ -1,19 +1,21 @@
 
1
  gradio==4.29.0
2
- gradio_client==0.16.1
3
- faiss-cpu==1.7.4
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  pandas==2.2.2
5
- filetype
6
- openpyxl
7
- python-dotenv
8
- tiktoken
9
- langgraph
10
- langsmith
11
- graphviz
12
- langchain
13
- langchain-community
14
- langchain-core
15
- langchain-experimental
16
- langchain-openai
17
- langgraph
18
- langsmith
19
- openai
 
1
+ faiss-cpu==1.8.0.post1
2
  gradio==4.29.0
3
+ graphviz==0.20.3
4
+ huggingface-hub==0.24.2
5
+ jq==1.7.0
6
+ langchain==0.2.11
7
+ langchain-community==0.2.10
8
+ langchain-core==0.2.23
9
+ langchain-experimental==0.0.63
10
+ langchain-huggingface==0.0.3
11
+ langchain-openai==0.1.17
12
+ langchain-text-splitters==0.2.2
13
+ langchainhub==0.1.20
14
+ langgraph==0.1.14
15
+ langsmith==0.1.93
16
+ openai==1.37.1
17
+ openpyxl==3.1.5
18
  pandas==2.2.2
19
+ pydantic==2.8.2
20
+ pydantic_core==2.20.1
21
+ tiktoken==0.7.0