sync-v0.0.4-fix (#502)

Shaunwei · Dec 29, 2023 · 0b33929 · 0b33929
1 parent 13f601f
commit 0b33929
Show file tree

Hide file tree

Showing 68 changed files with 15,456 additions and 9,684 deletions.
diff --git a/.env.example b/.env.example
@@ -4,16 +4,19 @@
 REBYTE_API_KEY=YOUR_API_KEY
 
 # Option 2: Alternate LLM APIs
-# Uncomment and configure the desired API
 # Supported APIs: OpenAI, Anthropic, Anyscale, Local LLM with Openai Compatiable API
+# Example values:
 # OpenAI: "gpt-4", "gpt-3.5-turbo-16k", etc.
 # Anthropic: "claude-instant-1", "claude-2", etc.
 # Anyscale: "meta-llama/Llama-2-70b-chat-hf", etc.
 # Local LLM: "localhost"
+# LLM_MODEL_USE overwrites frontend choices! Leave empty unless you know what you're doing!
+# LLM_MODEL_USE overwrites frontend choices! Leave empty unless you know what you're doing!
+# LLM_MODEL_USE overwrites frontend choices! Leave empty unless you know what you're doing!
 # LLM_MODEL_USE=gpt-3.5-turbo-16k
 
 # API Keys
-# Note that if not using ReByte, OPENAI_API_KEY is required for generating embeddings for
+# Note that if not using ReByte, an OPENAI_API_KEY is required for generating embeddings for
 # the knowledge base, no matter what LLM API is being used
 # OPENAI_API_KEY=YOUR_API_KEY
 # ANTHROPIC_API_KEY=YOUR_API_KEY

diff --git a/Dockerfile b/Dockerfile
@@ -35,4 +35,3 @@ RUN chmod +x /realtime_ai_character/entrypoint.sh
 
 # Run the application
 CMD ["/bin/sh", "/realtime_ai_character/entrypoint.sh"]
-
diff --git a/Dockerfile.postgres b/Dockerfile.postgres
@@ -0,0 +1,21 @@
+# Use the official PostgreSQL image as a base
+FROM postgres:14.1-alpine
+
+# Install necessary packages to build the extension
+RUN apk add --no-cache \
+    build-base \
+    git \
+    postgresql-dev
+
+# Clone and build pgvector
+RUN git clone https://github.com/ankane/pgvector.git \
+    && cd pgvector \
+    && make && make install
+
+# Cleanup unnecessary packages after installation
+RUN apk del build-base git postgresql-dev
+
+RUN echo "CREATE EXTENSION vector;" > /docker-entrypoint-initdb.d/init-vector-extension.sql
+
+# Set the shared preload libraries config
+RUN echo "shared_preload_libraries='pgvector'" >> /var/lib/postgresql/data/postgresql.conf
diff --git a/README.md b/README.md
@@ -9,7 +9,7 @@
 </p>
 
 <div align="center">
-    <a href="https://discord.gg/YV4U7Am2Xn">
+    <a href="https://realchar.ai/join-discord">
     <img src="https://img.shields.io/badge/discord-join%20chat-blue.svg?style=for-the-badge" alt="Join our Discord" height="20">
     </a>
     <a href="https://twitter.com/agishaun">
@@ -77,20 +77,122 @@ __Demo settings: Web, GPT4, ElevenLabs with voice clone, Chroma, Google Speech t
     <img src="https://storage.googleapis.com/assistly/static/realchar/compare.png">
 </div>
 
+## 📀 Quick Start - Installation via Docker
 
-## 👨‍🚀 Prerequisites
+1.  Create a new `.env` file
+    ```sh
+    cp .env.example .env
+    ```
+    Paste your API keys in `.env` file. A single [ReByte](#11-rebyte-api-key) or [OpenAI](#12-optional-openai-api-token) API key is enough to get started.
+
+    You can also configure other API keys if you have them.
 
-Before setting up this project, follow these instructions to meet the prerequisites:
+1.  Start the app with `docker-compose.yaml`
+    ```sh
+    docker compose up
+    ```
+    If you have issues with docker (especially on a non-Linux machine), please refer to https://docs.docker.com/get-docker/ (installation) and https://docs.docker.com/desktop/troubleshoot/overview/ (troubleshooting).
+
+1.  Open http://localhost:3000 and enjoy the app!
 
-### 1. Large Language Models
+## 💿 Developers - Installation via Python
+- **Step 1**. Clone the repo
+   ```sh
+   git clone https://github.com/Shaunwei/RealChar.git && cd RealChar
+    ```
+- **Step 2**. Install requirements
+
+    Install [portaudio](https://people.csail.mit.edu/hubert/pyaudio/) and [ffmpeg](https://ffmpeg.org/download.html) for audio
+    ```sh
+    # for mac
+    brew install portaudio
+    brew install ffmpeg
+    ```
+    ```sh
+    # for ubuntu
+    sudo apt update
+    sudo apt install portaudio19-dev
+    sudo apt install ffmpeg
+    ```
+    Note: 
+
+    - `ffmpeg>=4.4` is needed to work with `torchaudio>=2.1.0`
+
+    - Mac users may need to add ffmpeg library path to `DYLD_LIBRARY_PATH` for torchaudio to work:
+        ```sh
+        export DYLD_LIBRARY_PATH=/opt/homebrew/lib:$DYLD_LIBRARY_PATH
+        ```
+
+    Then install all python requirements
+    ```sh
+    pip install -r requirements.txt
+    ```
+    If you need a faster local speech to text, install whisperX
+    ```sh
+    pip install git+https://github.com/m-bain/whisperx.git
+    ```
+- **Step 3**. Create an empty [sqlite](https://www.sqlite.org/index.html) database if you have not done so before
+    ```sh
+    sqlite3 test.db "VACUUM;"
+    ```
+- **Step 4**. Run db upgrade
+    ```sh
+    alembic upgrade head
+    ```
+    This ensures your database schema is up to date. Please run this after every time you pull the main branch.
+- **Step 5**. Setup `.env`:
+    ```sh
+    cp .env.example .env
+    ```
+    Update API keys and configs following the instructions in the `.env` file.
+    > Note that some features require a working login system. You can get your own OAuth2 login for free with [Firebase](https://firebase.google.com/) if needed. To enable, set `USE_AUTH` to `true` and fill in the `FIREBASE_CONFIG_PATH` field. Also fill in Firebase configs in `client/next-web/.env`.
+- **Step 6**. Run backend server with `cli.py` or use uvicorn directly
+    ```sh
+    python cli.py run-uvicorn
+    # or
+    uvicorn realtime_ai_character.main:app
+    ```
+- **Step 7**. Run frontend client:
+    - web client:
+
+        Create an `.env` file under `client/next-web/`
+        ```sh
+        cp client/next-web/.env.example client/next-web/.env
+        ```
+        Adjust `.env` according to the instruction in `client/next-web/README.md`.
+
+        Start the frontend server:
+        ```sh
+        python cli.py next-web-dev
+        # or
+        cd client/next-web && npm run dev
+        # or
+        cd client/next-web && npm run build && npm run start
+        ```
+        After running these commands, a local development server will start, and your default web browser will open a new tab/window pointing to this server (usually http://localhost:3000).
+    - (Optional) Terminal client:
+
+        Run the following command in your terminal
+        ```sh
+        python client/cli.py
+        ```
+    - (Optional) mobile client:
+
+        open `client/mobile/ios/rac/rac.xcodeproj/project.pbxproj` in Xcode and run the app
+- **Step 8**. Select one character to talk to, then start talking. Use **GPT4** for better conversation and **Wear headphone** for best audio(avoid echo)
+
+Note if you want to remotely connect to a RealChar server, SSL set up is required to establish the audio connection. 
+
+## 👨‍🚀 API Keys and Configurations
+
+### 1. LLMs
 
 ### 1.1 ReByte API Key
 To get your ReByte API key, follow these steps:
 
 1. Go to the [ReByte website](https://rebyte.ai/) and sign up for an account if you haven't already.
 1. Once you're logged in, go to Settings > API Keys.
 1. Generate a new API key by clicking on the "Generate" button.
-1. Prepare to use it during configuration.
 
 ### 1.2 (Optional) OpenAI API Token
 <details><summary>👇click me</summary>
@@ -101,7 +203,6 @@ To get your OpenAI API token, follow these steps:
 1. Go to the [OpenAI website](https://beta.openai.com/signup/) and sign up for an account if you haven't already.
 1. Once you're logged in, navigate to the [API keys page](https://beta.openai.com/account/api-keys).
 1. Generate a new API key by clicking on the "Create API Key" button.
-1. Prepare to use it during configuration.
 
 (Optional) To use Azure OpenAI API instead, refer to the following section:
 
@@ -135,7 +236,6 @@ To get your Anthropic API token, follow these steps:
 1. Go to the [Anthropic website](https://docs.anthropic.com/claude/docs/getting-started-with-claude) and sign up for an account if you haven't already.
 1. Once you're logged in, navigate to the [API keys page](https://console.anthropic.com/account/keys).
 1. Generate a new API key by clicking on the "Create Key" button.
-1. Prepare to use it during configuration.
 </details>
 
 ### 1.4 (Optional) Anyscale API Token
@@ -146,12 +246,11 @@ To get your Anyscale API token, follow these steps:
 1. Go to the [Anyscale website](https://www.anyscale.com/) and sign up for an account if you haven't already.
 1. Once you're logged in, navigate to the [Credentials page](https://app.endpoints.anyscale.com/credentials).
 1. Generate a new API key by clicking on the "Generate credential" button.
-1. Prepare to use it during configuration.
 </details>
 
 ### 2. Speech to Text
 
-We support [whisperX](https://github.com/m-bain/whisperX) as the local speech to text engine. Work with CPU and NVIDIA GPU.
+We support [faster-whisper](https://github.com/SYSTRAN/faster-whisper) and [whisperX](https://github.com/m-bain/whisperX) as the local speech to text engines. Work with CPU and NVIDIA GPU.
 
 ### 2.1 (Optional) Google Speech-to-Text API
 <details><summary>👇click me</summary>
@@ -160,12 +259,14 @@ To get your Google Cloud API credentials.json, follow these steps:
 
 1. Go to the [GCP website](https://cloud.google.com/speech-to-text/docs/before-you-begin) and sign up for an account if you haven't already.
 2. Follow the guide to create a project and enable Speech to Text API
-3. Put `google_credentials.json` in the root folder of this project. Check [GCP website](https://cloud.google.com/speech-to-text/docs/before-you-begin#set_your_authentication_environment_variable)
+3. Put `google_credentials.json` in the root folder of this project. Check [Create and delete service account keys](https://cloud.google.com/iam/docs/keys-create-delete#iam-service-account-keys-create-console)
 4. Change `SPEECH_TO_TEXT_USE` to use `GOOGLE` in your `.env` file
 </details>
 
 ### 2.2 (Optional) OpenAI Whisper API
 <details><summary>👇click me</summary>
+
+Same as [OpenAI API Token](#12-optional-openai-api-token)
 </details>
 
 ### 3. Text to Speech
@@ -180,126 +281,20 @@ Edge TTS is the default and is free to use.
     Visit [ElevenLabs](https://beta.elevenlabs.io/) to create an account. You'll need this to access the text to speech and voice cloning features.
 
 1. In your Profile Setting, you can get an API Key.
-1. Prepare to use it during configuration.
 
 </details>
 
 ### 3.2 (Optional) Google Text-to-Speech API
 
-## 💿 Installation via Python
-- **Step 1**. Clone the repo
-   ```sh
-   git clone https://github.com/Shaunwei/RealChar.git && cd RealChar
-    ```
-- **Step 2**. Install requirements
-
-    Install [portaudio](https://people.csail.mit.edu/hubert/pyaudio/) and [ffmpeg](https://ffmpeg.org/download.html) for audio
-    ```sh
-    # for mac
-    brew install portaudio
-    brew install ffmpeg
-    ```
-    ```sh
-    # for ubuntu
-    sudo apt update
-    sudo apt install portaudio19-dev
-    sudo apt install ffmpeg
-    ```
-    Note: 
-
-    - `ffmpeg>=4.4` is needed to work with `torchaudio>=2.1.0`
-
-    - Mac users may need to add ffmpeg library path to `DYLD_LIBRARY_PATH` for torchaudio to work:
-        ```sh
-        export DYLD_LIBRARY_PATH=/opt/homebrew/lib:$DYLD_LIBRARY_PATH
-        ```
-
-    Then install all python requirements
-    ```sh
-    pip install -r requirements.txt
-    ```
-    If you need a faster local speech to text, install whisperX
-    ```sh
-    pip install git+https://github.com/m-bain/whisperx.git
-    ```
-- **Step 3**. Create an empty [sqlite](https://www.sqlite.org/index.html) database if you have not done so before
-    ```sh
-    sqlite3 test.db "VACUUM;"
-    ```
-- **Step 4**. Run db upgrade
-    ```sh
-    alembic upgrade head
-    ```
-    This ensures your database schema is up to date. Please run this after every time you pull the main branch.
-- **Step 5**. Setup `.env`:
-    ```sh
-    cp .env.example .env
-    ```
-    Update API keys and configs following the instructions in the `.env` file.
-    > Note that some features require a working login system. You can get your own OAuth2 login for free with [Firebase](https://firebase.google.com/) if needed. To enable, set `USE_AUTH` to `true` and fill in the `FIREBASE_CONFIG_PATH` field. Also fill in Firebase configs in `client/next-web/.env`.
-- **Step 6**. Run backend server with `cli.py` or use uvicorn directly
-    ```sh
-    python cli.py run-uvicorn
-    # or
-    uvicorn realtime_ai_character.main:app
-    ```
-- **Step 7**. Run frontend client:
-    - web client:
-
-        Create an `.env` file under `client/next-web/`
-        ```sh
-        cp client/next-web/.env.example client/next-web/.env
-        ```
-        Adjust `.env` according to the instruction in `client/next-web/README.md`.
-
-        Start the frontend server:
-        ```sh
-        python cli.py next-web-dev
-        # or
-        cd client/next-web && npm run dev
-        # or
-        cd client/next-web && npm run build && npm run start
-        ```
-        After running these commands, a local development server will start, and your default web browser will open a new tab/window pointing to this server (usually http://localhost:3000).
-    - (Optional) Terminal client:
-
-        Run the following command in your terminal
-        ```sh
-        python client/cli.py
-        ```
-    - (Optional) mobile client:
-
-        open `client/mobile/ios/rac/rac.xcodeproj/project.pbxproj` in Xcode and run the app
-- **Step 8**. Select one character to talk to, then start talking. Use **GPT4** for better conversation and **Wear headphone** for best audio(avoid echo)
-
-Note if you want to remotely connect to a RealChar server, SSL set up is required to establish the audio connection. 
-
-## (Optional) 📀 Installation via Docker
 <details><summary>👇click me</summary>
 
-1. Initialize and update the database
-    ```sh
-    sqlite3 test.db "VACUUM;"
-    alembic upgrade head
-    ```
-
-1. Configure `.env`
-    ```sh
-    cp .env.example .env
-    ```
-    Update API keys and configs following the instructions in the `.env` file.
-
-1. Start the app with `docker-compose.yaml`
-    ```sh
-    docker compose up
-    ```
-    If you have issues with docker (especially on a non-Linux machine), please refer to https://docs.docker.com/get-docker/ (installation) and https://docs.docker.com/desktop/troubleshoot/overview/ (troubleshooting).
+To get your Google Cloud API credentials.json, follow these steps:
 
-1. Open http://localhost:3000 to access the web app
+1. Go to the [GCP website](https://cloud.google.com/text-to-speech/docs/quickstart-client-libraries) and sign up for an account if you haven't already.
+2. Follow the guide to create a project and enable Text to Speech API
+3. Put `google_credentials.json` in the root folder of this project. Check [Create and delete service account keys](https://cloud.google.com/iam/docs/keys-create-delete#iam-service-account-keys-create-console)
 </details>
 
-<br/>
-
 ## (Optional) 🔥 Create Your Own Characters
 <details><summary>👇click me</summary>
 
@@ -373,4 +368,4 @@ Please check out our [Contribution Guide](contribute.md)!
 </a>
 
 ## 🎲 Community
-- Join us on [Discord](https://discord.gg/YV4U7Am2Xn)
+- Join us on [Discord](https://realchar.ai/join-discord)
diff --git a/client/next-web/.gitignore b/client/next-web/.gitignore
@@ -34,5 +34,3 @@ yarn-error.log*
 *.tsbuildinfo
 next-env.d.ts
 
-# zustand lib force to add
-!./lib
diff --git a/client/next-web/next.config.js b/client/next-web/next.config.js
@@ -1,4 +1,19 @@
 /** @type {import('next').NextConfig} */
-const nextConfig = {}
+const nextConfig = {
+  async redirects() {
+    return [
+      {
+        source: '/join-discord',
+        destination: 'https://discord.gg/e4AYNnFg2F',
+        permanent: false,
+      },
+      {
+        source: '/feedback',
+        destination: 'https://github.com/ReByteAI/bug-tracker',
+        permanent: false,
+      },
+    ];
+  },
+};
 
-module.exports = nextConfig
+module.exports = nextConfig;
Original file line number	Diff line number	Diff line change
Expand Up		@@ -35,4 +35,3 @@ RUN chmod +x /realtime_ai_character/entrypoint.sh

		# Run the application
		CMD ["/bin/sh", "/realtime_ai_character/entrypoint.sh"]