v0.10.0 (#80)

## 🌟 TL;DR - Key Highlights

- 🧪 **Complete Evaluation Framework** - Generate synthetic test data,
run batch experiments, and visualize results with interactive web
dashboard
- 🐧 **Linux Support** - Native CLI and UI (RAUX) support for Ubuntu with
unified cross-platform installation (currently supports iGPU via
llama.cpp/Vulkan backend using the Lemonade server)
- 🗣️ **Enhanced Voice & Chat and new SDKs** - Introduced a new Talk SDK
with real-time transcription and comprehensive Chat SDK with
conversation memory
- 📝 **AI Summarizer** - Intelligent meeting transcript and email
summarization with multiple output formats (PDF, HTML, JSON)
- 🎨 **Blender Integration** - Natural language 3D modeling through MCP
server with real-time scene manipulation

## ⚠️ Breaking Changes

- **CLI Command Update**: `gaia-cli` has been renamed to `gaia`
throughout the codebase
  - **Before**: `gaia-cli llm "Hello world"`
  - **After**: `gaia llm "Hello world"`
- **Agent Server Architecture**: Removed HTTP/WebSocket agent server
dependencies for text-based interactions
- **Parameter Changes**: Removed `--agent-name`, `--host`, `--port`
parameters from `prompt`, `chat`, `talk`, and `stats` commands

## 🚀 Major Features

### Enhanced Evaluation Framework
- **Comprehensive workflow documentation** with step-by-step examples
for meeting transcripts, emails, document Q&A, and third-party model
testing
- **Improved evaluation metrics** with time tracking for summary
generation and percentage-based quality scores
- **Robust experiment management** with crash recovery and selective
re-runs for new models
- **Enhanced reporting** with final results tables, bar charts, and
colored score legends
- **Interactive web visualization tool** for exploring evaluation
results with real-time experiment comparison
- **Synthetic data generation** for creating test datasets without
privacy concerns

**📖 Documentation:** See
[eval.md](https://github.com/amd/gaia/blob/main/docs/eval.md) for
complete evaluation workflows

**💡 Quick Start:**
```bash
# Complete evaluation workflow
gaia groundtruth -d ./test_data --use-case summarization -o ./groundtruth
gaia batch-experiment -c experiment_config.json -i ./groundtruth/consolidated_summarization_groundtruth.json -o ./experiments
gaia visualize --experiments-dir ./experiments --evaluations-dir ./evaluation
```

### Linux Platform Support
- **Full Linux CLI support** with complete Lemonade server integration
- **Cross-platform Python isolation** using standalone distributions
- **Enhanced CI/CD pipeline** with dedicated Linux testing workflows
- **GAIA UI (RAUX) Linux support** with native Ubuntu compatibility and
unified installation strategy

**📖 Documentation:** See
[cli.md](https://github.com/amd/gaia/blob/main/docs/cli.md) for
cross-platform usage and
[ui.md](https://github.com/amd/gaia/blob/main/docs/ui.md) for UI setup
**💡 Try it:** `gaia --version` or `gaia llm "Hello from Linux!"`

### Talk SDK and Audio Pipeline
- **Unified voice/text chat integration** with comprehensive SDK
- **Improved audio processing** with real-time transcription and
diagnostics
- **LLMClient streaming integration** replacing WebSocket architecture

**📖 Documentation:** See
[talk.md](https://github.com/amd/gaia/blob/main/docs/talk.md) for voice
interaction setup
**💡 Try it:** `gaia talk --help` or start a voice conversation with
`gaia talk`

### GAIA Summarizer Tool
- **AI-powered summarization** for meeting transcripts and emails
- **Multiple output formats** (JSON, PDF, HTML, email) with batch
processing
- **Customizable summary styles** (executive, bullets, detailed, action
items)
- **Auto-detection** of content type (transcript vs email) for optimized
processing
- **Batch processing** for entire directories of files

**📖 Documentation:** See
[cli.md](https://github.com/amd/gaia/blob/main/docs/cli.md) and
[features.md](https://github.com/amd/gaia/blob/main/docs/features.md)
for complete summarization workflows and all available options

**💡 Quick Start:**
```bash
# Summarize meeting transcript with multiple styles
gaia summarize -i meeting_transcript.txt --styles executive action_items
```

### Chat SDK
- **Comprehensive chat interface** with conversation memory and session
management
- **Multiple abstraction levels** from simple one-off questions to
advanced session handling
- **Assistant naming support** for personalized AI interactions
- **Streaming responses** with real-time output in interactive mode
- **Rich interactive commands** (`/clear`, `/history`, `/system`,
`/model`, `/stats`)

**📖 Documentation:** See `chat.md` for SDK integration guide

**💡 Quick Start:**
```bash
# Interactive chat with conversation memory
gaia chat
```

### Enhanced Blender Integration
- **Natural language 3D modeling** through MCP (Model Context Protocol)
server integration
- **Comprehensive scene management** with object creation, materials,
and transformations
- **Interactive planning system** for complex 3D scene creation
- **CLI command support** with example-based learning and custom queries
- **Real-time Blender communication** for immediate 3D visualization

**📖 Documentation:** See
[blender.md](https://github.com/amd/gaia/blob/main/docs/blender.md) for
setup and MCP server configuration

**💡 Quick Start:**
```bash
# Natural language 3D modeling
gaia blender --query "Create a red cube and blue sphere"
```

## 🔧 Architecture Improvements

- **Simplified CLI architecture** with direct LLM communication (removed
agent server dependencies)
- **Enhanced Blender MCP integration** with real-time 3D scene
manipulation
- **Improved error handling** and resource cleanup across components
- **Performance optimizations** for cross-platform deployment

## 🐛 Bug Fixes

- **Chat CLI improvements** with restored interactive conversation
support and conversation history management
- **Talk CLI enhancements** with improved audio processing and real-time
transcription reliability
- **Installation verification fixes** with simplified Lemonade
verification and enhanced logging
- **Cross-platform compatibility** improvements for both Windows and
Linux environments

## 📖 Documentation & Tooling

- **Comprehensive evaluation documentation** with practical examples and
workflows
- **Cost estimation tools** for Claude API usage tracking with detailed
breakdowns
- **Enhanced testing infrastructure** with dedicated Chat SDK CI
workflows
- **Updated installation processes** with improved reliability
- **Interactive web applications** for evaluation visualization and
result exploration

## 🚀 Installation & Upgrade

### Quick Installation
- **Windows**: Simply download and run
[gaia-windows-setup.exe](https://github.com/amd/gaia/releases/download/v0.10.0/gaia-windows-setup.exe)
- **Linux (UI)**: Follow the steps outlined in the [UI installation
guide](https://github.com/amd/gaia/blob/main/docs/ui.md)
- **Linux (CLI)**: Follow the steps outlined in the [GAIA developer
guide](https://github.com/amd/gaia/blob/v0.10.0/docs/dev.md#setup-and-installation)

### Developer Installation
```bash
# Install GAIA with all features
pip install -e .[talk,dev,eval]

### Upgrading from v0.9.x
```bash
# Update your installation
pip install --upgrade gaia

# Update CLI commands (breaking change)
# Old: gaia-cli llm "Hello"
# New: gaia llm "Hello"

# Verify installation
gaia --version
gaia llm "Test query to verify functionality"
```

### Requirements
- **Lemonade Server**: Required for LLM functionality (`lemonade-server serve`)
- **Blender 4.3+**: Required for 3D modeling features
- **Node.js**: Required for evaluation web visualizer

Author: kovtcharov

.claude/settings.local.json

@@ -0,0 +1,10 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(python:*)",
+      "Bash(where python)",
+      "Bash(py --version)",
+    ],
+    "deny": []
+  }
+}

.cursor/.cursorignore

@@ -0,0 +1 @@
+.env

.env.example

@@ -0,0 +1,8 @@
+OPENAI_API_KEY=
+GITHUB_TOKEN=
+YOUTUBE_API_KEY=
+GROQ_API_KEY=
+PHOENIX_API_KEY=
+HUGGINGFACE_ACCESS_TOKEN=
+HF_TOKEN=
+ANTHROPIC_API_KEY=

.github/actions/install-lemonade/action.yml

@@ -22,18 +22,51 @@ runs:
         Add-MpPreference -ExclusionProcess "Lemonade_Server_Installer.exe"
 
         # Download and run installer
-        Invoke-WebRequest -Uri "https://github.com/lemonade-sdk/lemonade/releases/download/v$env:LEMONADE_VERSION/Lemonade_Server_Installer.exe" -OutFile "C:\temp\Lemonade_Server_Installer.exe"
-
-        $installPath = "C:\Users\nimbys\AppData\Local\lemonade_server"
-        Write-Host "Installing to: $installPath"
-
-        $process = Start-Process -FilePath "C:\temp\Lemonade_Server_Installer.exe" -ArgumentList "/S", "/Extras=hybrid", "/Models=Qwen2.5-0.5B-Instruct-CPU", "/D=$installPath" -Wait -PassThru
-
-        if ($process.ExitCode -ne 0) {
-          Write-Host "Lemonade installer failed with exit code: $($process.ExitCode)"
+        $installerPath = "C:\temp\Lemonade_Server_Installer.exe"
+        
+        # Remove existing file if it exists
+        if (Test-Path $installerPath) {
+          Write-Host "Removing existing installer file"
+          Remove-Item $installerPath -Force
+        }
+        
+        Invoke-WebRequest -Uri "https://github.com/lemonade-sdk/lemonade/releases/download/v$env:LEMONADE_VERSION/Lemonade_Server_Installer.exe" -OutFile $installerPath -UseBasicParsing
+        
+        # Check downloaded file
+        if (Test-Path $installerPath) {
+          $fileInfo = Get-Item $installerPath
+          Write-Host "Downloaded installer: $($fileInfo.Length) bytes"
+          
+          # Basic sanity check - installer should be at least 100KB
+          if ($fileInfo.Length -lt 100000) {
+            Write-Host "ERROR: Downloaded file is suspiciously small ($($fileInfo.Length) bytes)"
+            Write-Host "This suggests we downloaded an error page instead of the installer"
+            
+            # Check if we got HTML error page (without -Raw and -TotalCount together)
+            $firstBytes = Get-Content $installerPath -Encoding Byte -TotalCount 200
+            $firstText = [System.Text.Encoding]::ASCII.GetString($firstBytes)
+            Write-Host "First 200 characters of downloaded file:"
+            Write-Host $firstText
+            exit 1
+          }
+        } else {
+          Write-Host "ERROR: Installer file not found after download"
           exit 1
         }
 
+    - name: Run Lemonade Installer
+      shell: powershell
+      run: |
+        Write-Host "Installing Lemonade Server..."
+        cd C:\temp
+        Start-Process -FilePath ".\Lemonade_Server_Installer.exe" -ArgumentList "/S /Extras=hybrid /Models=Llama-3.2-3B-Instruct-Hybrid /D=C:\Users\nimbys\AppData\Local\lemonade_server" -Wait
+        Write-Host "Installer completed"
+
+    - name: Verify Installation
+      shell: powershell  
+      run: |
+        $installPath = "C:\Users\nimbys\AppData\Local\lemonade_server"
+        
         # Remove exclusions after installation
         Remove-MpPreference -ExclusionPath "C:\temp\Lemonade_Server_Installer.exe"
         Remove-MpPreference -ExclusionProcess "Lemonade_Server_Installer.exe"
@@ -50,6 +83,10 @@ runs:
             & $lemonadeExe --version
             Write-Host "Lemonade Server installed successfully"
         } else {
-            Write-Host "Lemonade server executable not found"
+            Write-Host "Lemonade server executable not found at: $lemonadeExe"
+            if (Test-Path "$installPath\python\Scripts") {
+                Write-Host "Scripts directory contents:"
+                Get-ChildItem "$installPath\python\Scripts" | ForEach-Object { Write-Host "  - $($_.Name)" }
+            }
             exit 1
         }

.github/workflows/build_installer.yml

@@ -1,7 +1,11 @@
 # Copyright(C) 2024-2025 Advanced Micro Devices, Inc. All rights reserved.
 # SPDX-License-Identifier: MIT
 
-name: Build GAIA Installer
+# This workflow builds the Windows installer for GAIA using NSIS
+# Creates a Windows-specific installer package with all dependencies
+# Platform: Windows (NSIS-based installer creation)
+
+name: Build GAIA Installer (Windows)
 
 on:
   workflow_call:
@@ -17,14 +21,21 @@ on:
         value: ${{ jobs.build-installer.outputs.COMMIT_HASH }}
   push:
     branches: ["main"]
+    paths:
+      - "installer/**"
+      - "src/**"
   pull_request:
     branches: ["main"]
     types: [opened, synchronize, reopened, ready_for_review]
+    paths:
+      - "installer/**"
+      - "src/**"
   merge_group:
   workflow_dispatch:
 
 jobs:
   build-installer:
+    name: Build Windows Installer Package
     runs-on: windows-latest
     if: github.event_name != 'pull_request' || github.event.pull_request.draft == false || contains(github.event.pull_request.labels.*.name, 'ready_for_ci')
     outputs:
@@ -81,12 +92,12 @@ jobs:
           echo "VERSION=$version" >> $env:GITHUB_OUTPUT
           Write-Host "Extracted version: $version"
 
-      - name: Build the GAIA installer
+      - name: Build the Windows installer using NSIS
         run: |
           cd installer
           & 'C:\Program Files (x86)\NSIS\makensis.exe' /DOGA_TOKEN="${{ secrets.OGA_PUBLIC_TOKEN }}" 'Installer.nsi'
 
-          # Verify installer was created successfully
+          # Verify Windows installer was created successfully
           if (Test-Path "gaia-windows-setup.exe") {
             Write-Host "gaia-windows-setup.exe has been created successfully."
           } else {
@@ -102,11 +113,10 @@ jobs:
           echo "INSTALLER_HASH=$hash" >> $env:GITHUB_OUTPUT
           Write-Host "Installer SHA256: $hash"
 
-      - name: Upload installer
+      - name: Upload Windows installer artifact
         uses: actions/upload-artifact@v4
         with:
           name: gaia-windows-installer-${{ steps.extract_version.outputs.VERSION }}-${{ steps.get_commit.outputs.COMMIT_HASH }}
           path: installer\gaia-windows-setup.exe
-
           if-no-files-found: error
           retention-days: 7

.github/workflows/lint.yml

@@ -0,0 +1,62 @@
+# Copyright(C) 2024-2025 Advanced Micro Devices, Inc. All rights reserved.
+# SPDX-License-Identifier: MIT
+
+# This workflow runs code quality checks (linting) for the entire codebase
+# Provides fast feedback on code quality before running platform-specific tests
+# Platform: Linux/Ubuntu (cross-platform code analysis)
+
+name: Code Quality (Lint)
+
+on:
+  workflow_call:
+  push:
+    branches: ["main"]
+    paths:
+      - "src/**"
+      - "tests/**"
+      - "installer/**"
+      - "groundtruth/**"
+      - "test_data/**"
+  pull_request:
+    branches: ["main"]
+    types: [opened, synchronize, reopened, ready_for_review]
+    paths:
+      - "src/**"
+      - "tests/**"
+      - "installer/**"
+      - "groundtruth/**"
+      - "test_data/**"
+  merge_group:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  lint:
+    name: Run Code Quality Checks
+    runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request' || github.event.pull_request.draft == false || contains(github.event.pull_request.labels.*.name, 'ready_for_ci')
+    steps:
+      - uses: actions/checkout@v4
+      
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          
+      - name: Install linting dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install black pylint
+          
+      - name: Lint with Black
+        run: |
+          black --check --verbose --config pyproject.toml installer src tests
+          
+      - name: PyLint
+        run: |
+          # Install minimal dependencies needed for pylint to work
+          pip install -e .
+          # Run pylint matching the PowerShell script configuration
+          python -m pylint src/gaia --rcfile .pylintrc --disable C0103,C0301,W0246,W0221,E1102,R0401,E0401,W0718

.github/workflows/publish_installer.yml

@@ -3,10 +3,17 @@ name: Publish GAIA Installer
 on:
   push:
     branches: ["main"]
+    paths:
+      - "installer/**"
+      - "src/**"
     tags:
       - v*
   pull_request:
     branches: ["main"]
+    types: [opened, synchronize, reopened, ready_for_review]
+    paths:
+      - "installer/**"
+      - "src/**"
   merge_group:
   workflow_dispatch:
 

.github/workflows/test_eval.yml

@@ -0,0 +1,100 @@
+# Copyright(C) 2024-2025 Advanced Micro Devices, Inc. All rights reserved.
+# SPDX-License-Identifier: MIT
+
+# This workflow runs tests for the evaluation tool
+# Triggers when eval source code or tests are modified
+# Platform: Windows only
+
+name: Test Evaluation Tool
+
+on:
+  workflow_call:
+  push:
+    branches: ["main"]
+    paths:
+      - "src/gaia/eval/**"
+      - "src/gaia/eval/configs/**"
+      - "src/gaia/eval/webapp/**"
+      - "tests/test_eval*.py"
+      - "groundtruth/**"
+      - "test_data/**"
+  pull_request:
+    branches: ["main"]
+    types: [opened, synchronize, reopened, ready_for_review]
+    paths:
+      - "src/gaia/eval/**"
+      - "src/gaia/eval/configs/**"
+      - "src/gaia/eval/webapp/**"
+      - "tests/test_eval*.py"
+      - "groundtruth/**"
+      - "test_data/**"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  test-eval-windows:
+    name: Test Eval Tool (Windows)
+    runs-on: windows-latest
+    if: github.event_name != 'pull_request' || github.event.pull_request.draft == false || contains(github.event.pull_request.labels.*.name, 'ready_for_ci')
+    timeout-minutes: 10  # 2 minute target but allow some buffer
+    
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e .
+          pip install pytest pytest-cov pytest-mock
+          pip install anthropic rich
+          
+      - name: Run eval unit tests
+        run: |
+          pytest tests/test_eval.py -v --cov=src/gaia/eval --cov-report=term-missing
+          
+      - name: Test eval CLI commands
+        run: |
+          # Test help command
+          python -m gaia.cli eval --help
+          # Test visualize help
+          python -m gaia.cli visualize --help
+          
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '18'
+          
+      - name: Test webapp functionality
+        run: |
+          cd src/gaia/eval/webapp
+          # Install dependencies
+          npm install
+          # Run syntax checks
+          npm test
+          # Test that server can start (Windows-compatible version)
+          $env:PORT = 3456  # Use non-default port to avoid conflicts
+          $process = Start-Process node -ArgumentList "server.js" -PassThru -ErrorAction Stop
+          Start-Sleep -Seconds 3
+          if ($process.HasExited) {
+            Write-Error "Server failed to start or crashed immediately"
+            exit 1
+          }
+          # Try to connect to the server
+          try {
+            $response = Invoke-WebRequest -Uri "http://localhost:3456" -TimeoutSec 5 -UseBasicParsing
+            Write-Output "Server responded with status: $($response.StatusCode)"
+          } catch {
+            Write-Error "Server did not respond to HTTP request"
+            Stop-Process -Id $process.Id -Force -ErrorAction SilentlyContinue
+            exit 1
+          }
+          Stop-Process -Id $process.Id -Force
+          Write-Output "Webapp server test passed"