feat: voice to image with gpt image 1 point 5

ai_agents/.env.example

@@ -14,6 +14,17 @@ WORKERS_MAX=100
 # Worker quit timeout in seconds
 WORKER_QUIT_TIMEOUT_SECONDS=60
 
+# ------------------------------
+# Frontend
+# ------------------------------
+
+# API server URL for the web UI
+AGENT_SERVER_URL=http://localhost:8080
+# TMAN Designer dev server URL for the web UI
+TEN_DEV_SERVER_URL=http://localhost:49483
+# Enable edit graph mode in the UI
+NEXT_PUBLIC_EDIT_GRAPH_MODE=true
+
 # ------------------------------
 # RTC
 # ------------------------------

ai_agents/agents/examples/doodler/.env.example

@@ -0,0 +1,12 @@
+# Required Environment Variables
+
+# Agora RTC (for voice input)
+AGORA_APP_ID=your_agora_app_id_here
+AGORA_APP_CERTIFICATE=your_agora_certificate_here  # Optional
+
+# OpenAI (for ASR, LLM, and Image Generation)
+OPENAI_API_KEY=sk-your_openai_api_key_here
+
+# Optional Customization
+OPENAI_MODEL=gpt-4o-mini  # LLM model
+OPENAI_BASE_URL=https://api.openai.com/v1  # Custom endpoint

ai_agents/agents/examples/doodler/Dockerfile

@@ -0,0 +1,83 @@
+FROM ghcr.io/ten-framework/ten_agent_build:0.7.12 AS builder
+
+ARG USE_AGENT=agents/examples/voice-assistant
+
+WORKDIR /app
+
+COPY .env.example .env
+COPY server/ server/
+COPY agents/scripts/ agents/scripts/
+COPY agents/ten_packages/ agents/ten_packages/
+COPY ${USE_AGENT}/frontend/ ${USE_AGENT}/frontend/
+
+# Copy tenapp files explicitly to avoid symlink issues
+COPY ${USE_AGENT}/tenapp/go.* ${USE_AGENT}/tenapp/
+COPY ${USE_AGENT}/tenapp/main.go ${USE_AGENT}/tenapp/
+COPY ${USE_AGENT}/tenapp/manifest* ${USE_AGENT}/tenapp/
+COPY ${USE_AGENT}/tenapp/property.json ${USE_AGENT}/tenapp/
+COPY ${USE_AGENT}/tenapp/scripts/ ${USE_AGENT}/tenapp/scripts/
+
+# Copy extension directories that are actual directories (not symlinks)
+COPY ${USE_AGENT}/tenapp/ten_packages/extension/main_python/ ${USE_AGENT}/tenapp/ten_packages/extension/main_python/
+
+# Copy other example files
+COPY ${USE_AGENT}/README.md ${USE_AGENT}/
+COPY ${USE_AGENT}/Taskfile*.yml ${USE_AGENT}/
+
+RUN cd /app/${USE_AGENT} && \
+  task install && task release
+
+# Build frontend in builder stage (bun already done by task install)
+WORKDIR /app/${USE_AGENT}/frontend
+RUN NEXT_PUBLIC_EDIT_GRAPH_MODE=false bun run build
+WORKDIR /app
+
+FROM ubuntu:22.04
+
+ARG USE_AGENT=agents/examples/voice-assistant
+
+RUN apt-get clean && apt-get update && apt-get install -y --no-install-recommends \
+  libasound2 \
+  libgstreamer1.0-dev \
+  libunwind-dev \
+  libc++1 \
+  libssl-dev \
+  python3 \
+  python3-venv \
+  python3-pip \
+  python3-dev \
+  jq vim \
+  ca-certificates \
+  curl \
+  unzip \
+  && apt-get clean && rm -rf /var/lib/apt/lists/* && rm -rf /tmp/*
+
+# Install Node.js 20
+RUN curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
+  && apt-get install -y nodejs
+
+# Install Bun using the official install script
+RUN curl -fsSL https://bun.com/install | bash
+# Add Bun to the PATH (if not already added by the install script)
+ENV PATH="/root/.bun/bin:$PATH"
+
+# Install Task
+RUN sh -c "$(curl --location https://taskfile.dev/install.sh)" -- -d -b /usr/local/bin
+
+WORKDIR /app
+
+COPY --from=builder /app/${USE_AGENT}/tenapp/.release/ /app/agents/
+COPY --from=builder /app/server/bin/api /app/server/bin/api
+COPY --from=builder /usr/local/lib /usr/local/lib
+COPY --from=builder /usr/lib/python3 /usr/lib/python3
+COPY --from=builder /usr/local/bin/tman /usr/local/bin/tman
+
+# Copy built frontend from builder stage
+COPY --from=builder /app/${USE_AGENT}/frontend/ /app/frontend/
+
+# Copy Docker Taskfile
+COPY --from=builder /app/${USE_AGENT}/Taskfile.docker.yml /app/Taskfile.docker.yml
+
+EXPOSE 8080 3000
+
+ENTRYPOINT ["task", "-t", "Taskfile.docker.yml", "run-prod"]