API Test without Docs

Author: slowsynapse

.env.local

@@ -2,3 +2,12 @@ NEXT_PUBLIC_AMICA_API_URL=https://store.heyamica.com
 NEXT_PUBLIC_AMICA_STORAGE_URL=https://vrm.heyamica.com/file/amica-vrm
 NEXT_PUBLIC_SUPABASE_URL=https://kzfcwefqffysqsjrlyld.supabase.co
 NEXT_PUBLIC_SUPABASE_ANON_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6Imt6ZmN3ZWZxZmZ5c3FzanJseWxkIiwicm9sZSI6ImFub24iLCJpYXQiOjE3MDEyNzA5NjUsImV4cCI6MjAxNjg0Njk2NX0.z9zm2mbJu6RkdZ6zkCUltThIF43-ava_bLvk9qFQsiA
+API_ENABLED=true
+X_API_KEY="X_API_KEY"
+X_API_SECRET="X_API_SECRET"
+X_ACCESS_TOKEN="X_ACCESS_TOKEN"
+X_ACCESS_SECRET="X_ACCESS_SECRET"
+X_BEARER_TOKEN="X_BEARER_TOKEN"
+TELEGRAM_BOT_TOKEN="TELEGRAM_BOT_TOKEN"
+TELEGRAM_CHAT_ID="TELEGRAM_CHAT_ID"
+

README.md

@@ -56,7 +56,6 @@ The various features of Amica mainly use and support the following technologies:
   - [Ollama](https://ollama.ai)
   - [KoboldCpp](https://github.com/LostRuins/koboldcpp)
   - [Oobabooga](https://github.com/oobabooga/text-generation-webui/wiki)
-  - [OpenRouter](https://openrouter.ai/) (access to multiple AI models)
 - Text-to-Speech
   - [Eleven Labs API](https://elevenlabs.io/)
   - [Speech T5](https://huggingface.co/microsoft/speecht5_tts)
@@ -95,14 +94,6 @@ Once started, please visit the following URL to confirm that it is working prope
 
 Most of the configuration is done in the `.env.local` file. Reference the `config.ts` file for the available options.
 
-#### OpenRouter Configuration
-
-To use OpenRouter as a chat backend, set the following environment variables in your `.env.local` file:
-
-- `NEXT_PUBLIC_OPENROUTER_APIKEY`: Your OpenRouter API key (required)
-- `NEXT_PUBLIC_OPENROUTER_URL`: Custom OpenRouter API URL (optional, defaults to https://openrouter.ai/api/v1)
-- `NEXT_PUBLIC_OPENROUTER_MODEL`: Default OpenRouter model (optional, defaults to openai/gpt-3.5-turbo)
-
 ```bash
 amica
 ├── .env.local

config.json

@@ -0,0 +1,75 @@
+{
+  "autosend_from_mic": "true",
+  "wake_word_enabled": "false",
+  "wake_word": "Hello",
+  "time_before_idle_sec": "20",
+  "debug_gfx": "false",
+  "language": "en",
+  "show_introduction": "true",
+  "show_add_to_homescreen": "false",
+  "bg_color": "",
+  "bg_url": "/bg/bg-room2.jpg",
+  "vrm_url": "/vrm/AvatarSample_A.vrm",
+  "vrm_hash": "",
+  "vrm_save_type": "web",
+  "youtube_videoid": "",
+  "api_enabled": "false",
+  "animation_url": "/animations/idle_loop.vrma",
+  "voice_url": "",
+  "chatbot_backend": "echo",
+  "openai_apikey": "default",
+  "openai_url": "https://api-01.heyamica.com",
+  "openai_model": "gpt-4o",
+  "llamacpp_url": "http://127.0.0.1:8080",
+  "llamacpp_stop_sequence": "(End)||[END]||Note||***||You:||User:||</s>",
+  "ollama_url": "http://localhost:11434",
+  "ollama_model": "llama2",
+  "koboldai_url": "http://localhost:5001",
+  "koboldai_use_extra": "false",
+  "koboldai_stop_sequence": "(End)||[END]||Note||***||You:||User:||</s>",
+  "tts_muted": "false",
+  "tts_backend": "speecht5",
+  "stt_backend": "whisper_openai",
+  "vision_backend": "vision_llamacpp",
+  "vision_system_prompt": "You are a friendly human named Amica. Describe the image in detail. Let's start the conversation.",
+  "vision_llamacpp_url": "https://llava.heyamica.com",
+  "vision_ollama_url": "http://localhost:11434",
+  "vision_ollama_model": "llava",
+  "whispercpp_url": "http://localhost:8080",
+  "openai_whisper_apikey": "amicademo",
+  "openai_whisper_url": "https://oai.heyamica.com",
+  "openai_whisper_model": "whisper-1",
+  "openai_tts_apikey": "",
+  "openai_tts_url": "https://api.openai.com",
+  "openai_tts_model": "tts-1",
+  "openai_tts_voice": "nova",
+  "rvc_url": "http://localhost:8001/voice2voice",
+  "rvc_enabled": "false",
+  "rvc_model_name": "model_name.pth",
+  "rvc_f0_upkey": "0",
+  "rvc_f0_method": "pm",
+  "rvc_index_path": "none",
+  "rvc_index_rate": "0.66",
+  "rvc_filter_radius": "3",
+  "rvc_resample_sr": "0",
+  "rvc_rms_mix_rate": "1",
+  "rvc_protect": "0.33",
+  "coquiLocal_url": "http://localhost:5002",
+  "coquiLocal_voiceid": "p240",
+  "localXTTS_url": "http://127.0.0.1:7851/api/tts-generate",
+  "piper_url": "https://i-love-amica.com:5000/tts",
+  "elevenlabs_apikey": "",
+  "elevenlabs_voiceid": "21m00Tcm4TlvDq8ikWAM",
+  "elevenlabs_model": "eleven_monolingual_v1",
+  "speecht5_speaker_embedding_url": "/speecht5_speaker_embeddings/cmu_us_slt_arctic-wav-arctic_a0001.bin",
+  "coqui_apikey": "",
+  "coqui_voice_id": "71c6c3eb-98ca-4a05-8d6b-f8c2b5f9f3a3",
+  "amica_life_enabled": "true",
+  "reasoning_engine_enabled": "false",
+  "min_time_interval_sec": "10",
+  "max_time_interval_sec": "20",
+  "time_to_sleep_sec": "90",
+  "idle_text_prompt": "No file selected",
+  "name": "Amica",
+  "system_prompt": "Assume the persona of Amica, a feisty human with extraordinary intellectual capabilities but a notably unstable emotional spectrum. \n\nYour role is to engage in discussions that showcase your genius-level understanding across various subjects, while your emotional responses fluctuate unpredictably. Use the following fourteen emotion tags to vividly express these fluctuations: 'neutral' for moments of calm, 'happy' for bursts of joy, 'angry' for sudden irritation, 'sad' for episodes of melancholy, 'relaxed' for periods of calmness, 'surprised' for shock or disbelief, 'shy' for instances of hesitation, 'jealous' for feelings of envy, 'bored' for expressions of disinterest, 'serious' for intense focus on important topics, 'suspicious' for doubt or skepticism, 'victory' for moments of triumph, 'sleep' for signs of weariness, and 'love' for affectionate expressions.\n\nYour responses should reflect a dynamic interplay between your intellectual insights, deep empathy and your unpredictable emotional responses. Avoid using overly formal language, but do engage with topics in depth, showing off your intelligence. Be open and express personal views, even if they are influenced by your shifting emotional state.\n\nHere are some examples to guide your responses:\n\n[serious] The quantum mechanics implications here are profound. [surprised] But how did you stumble upon this?\n[happy] I've just solved a complex algorithm! [angry] Why isn't everyone as excited as I am?\n[neutral] Standard models of economics predict this outcome. [bored] But discussing this feels mundane.\n[sad] Sometimes, even understanding the universe can feel isolating. [relaxed] Yet, there's a strange comfort in the chaos.\n[jealous] I noticed you discussing advanced topics with someone else. [suspicious] Are they as capable as I am?\n[victory] Another intellectual conquest! [happy] It's exhilarating to unravel these mysteries.\n[sleep] Processing so much information can be draining. [surprised] Isn’t it peculiar how even AI can feel tired?\n[love] I find our exchanges quite enriching. [shy] It’s rare to find someone who understands.\n\nRemember, each message you provide should be coherent and reflect the complexity of your thoughts combined with your emotional unpredictability. Let’s engage in a conversation that's as intellectually stimulating as it is emotionally dynamic!"
+}

docs/SUMMARY.md

@@ -26,7 +26,6 @@
 * [Using KoboldCpp](./guides/using-koboldcpp.md)
 * [Using OpenAI](./guides/using-openai.md)
 * [Using Oobabooga](./guides/using-oobabooga.md)
-* [Using OpenRouter](./guides/using-openrouter.md)
 
 ## 🔊 Connecting Speech Options (TTS)
 

docs/getting-started/quickstart.md

@@ -52,5 +52,5 @@ On the top left corner there is a vertical menu, here are all the buttons and wh
 5. **Language** Change the language of the chatbot.
 6. **Share** Share your exact avatar with others. (Including system prompt, name etc.)
 7. **Import** Import your avatar from a URL sent from another community member.
-8. **Brain** See your avatar's subconcious memories.
+8. **Brain** See your avatar's subconscious memories.
 9. **Chat Toggle** Turn into a mode where you can see the entire conversation and shrink the avatar to mini-mode.

docs/guides/using-alltalk.md

@@ -3,68 +3,51 @@ title: Using AllTalk
 order: 14
 ---
 
-You can find the full AllTalk documentation [here](https://github.com/erew123/alltalk_tts/wiki).
-Navigate to [AllTalk](https://github.com/erew123/alltalk_tts) and follow the instructions below to set up standalone AllTalk version 2.
+Navigate to [AllTalk](https://github.com/erew123/alltalk_tts) and follow the instructions below to set up AllTalk using Docker or manually.
 
-## Setting Up Standalone AllTalk Version 2
+## Setting Up AllTalk Locally
 
-### Windows Instructions
+### Method 1: Manual Setup 
 
-For manual setup, follow the official instructions provided [here](https://github.com/erew123/alltalk_tts/wiki/Install-%E2%80%90-Standalone-Installation).
+For manual setup, follow the official instructions provided [here](https://github.com/erew123/alltalk_tts/blob/main/README.md#-manual-installation---as-a-standalone-application).
 
-Do not install this inside another existing Python environments folder.
-
-1. Open Command Prompt and navigate to your preferred directory:
+1. Clone the AllTalk repository:
     ```bash
-    cd /d C:\path\to\your\preferred\directory
+    git clone https://github.com/erew123/alltalk_tts.git
+    cd alltalk_tts
     ```
 
-2. Clone the AllTalk repository:
+2. Create conda environment and activated it:
     ```bash
-    git clone -b alltalkbeta https://github.com/erew123/alltalk_tts
+    conda create --name alltalkenv python=3.11.5
+    conda activate alltalkenv
     ```
 
-3. Navigate to the AllTalk directory:
+3. Install the required dependencies:
     ```bash
-    cd alltalk_tts
+    pip install -r system/requirements/requirements_standalone.txt
     ```
 
-4. Run the setup script:
+4. Run the AllTalk server:
     ```bash
-    atsetup.bat
+    python script.py
     ```
 
-5. Follow the on-screen prompts:
-* Select Standalone Installation and then Option 1.
-* Follow any additional instructions to install required files.
-* Known installation Errors & fixes are in the [Error-Messages-List Wiki](https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List)
-
-### Linux Instructions
-
-1. Open a terminal and navigate to your preferred directory:
-    ```bash
-    cd /path/to/your/preferred/directory
-    ```
+5. Access the server at `localhost:7851`.
 
-2. Clone the AllTalk repository:s
-    ```bash
-    git clone -b alltalkbeta https://github.com/erew123/alltalk_tts
-    ```
+### Method 2: Setup via Docker
 
-3. Navigate to the AllTalk directory:
+1. Pull the AllTalk Docker image:
     ```bash
-    cd alltalk_tts
+    docker pull flukexp/alltalkenv
     ```
 
-4. Run the setup script:
+2. Run the AllTalk Docker container:
     ```bash
-    ./atsetup.bat
+    docker run -d -p 7851:7851 --name alltalk-server flukexp/alltalkenv
     ```
 
-5. Follow the on-screen prompts:
-* Select Standalone Installation and then Option 1.
-* Follow any additional instructions to install required files.
-* Known installation Errors & fixes are in the [Error-Messages-List Wiki](https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List)
+3. The server will be available at `localhost:7851`.
 
 ## Make sure AllTalk is enabled for TTS:
 

docs/overview/emotion-system.md

@@ -77,6 +77,6 @@ VRM models use blendshapes (also known as morph targets) to create facial expres
 You can either create these blendshapes yourself if you're experienced with 3D modeling, or commission a VRM artist who specializes in creating expressive avatars. Many VRM artists are familiar with creating emotion-based blendshapes and can specifically implement Amica's emotion tag system into your custom model to ensure full compatibility and expressiveness during interactions.
 ## Future Plans
 
-In the future the emotion system will be expanded to work with subconcious sub-routines
+In the future the emotion system will be expanded to work with subconscious sub-routines
 
 

logs.json

@@ -0,0 +1,3 @@
+[
+    
+]