Merge pull request #2 from noco-ai/v0.2.0

V0.2.0

.env

@@ -0,0 +1,3 @@
+GOLEM_VAULT_HOST=http://10.23.82.2:8200
+GOLEM_AMQP_HOST=10.23.82.4
+GOLEM_ID=golem1

README.md

@@ -13,6 +13,9 @@ require ExLlama and a Nvidia Ampere or better GPU for real-time results.
 
 These instructions should work to get the SpellBook framework up and running on Ubuntu 22. A Nvidia video card supported by ExLlama is required for routing.
 
+- Default username: admin
+- Default password: admin
+
 ### Docker Installation
 
 ```bash
@@ -35,6 +38,46 @@ sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin
 sudo groupadd docker
 sudo usermod -aG docker $USER
 sudo newgrp docker
+sudo shutdown -r now
+```
+
+### Build and Start Containers (No GPU)
+
+The docker-compose-nogpu.yml is useful for running the UI and middleware in a situation where you want another backend handling you GPUs and LLMs. For example
+if you are also using Text Generation UI and do not want to mess with it settings this compose file can be used to just run the UI, allowing you then to then connect it to the endpoint provided by Oobabooga or any other OpenAI compatible backend.
+
+```bash
+docker compose -f docker-compose-nogpu.yml build
+docker compose -f docker-compose-nogpu.yml up
+```
+
+### Build and Start Additional Workers (No GPU)
+
+If you have more than one server you can run additional Elemental Golem workers to give the UI access to more resources. A few steps need to be taken on the
+primary Spellbook server that is running the UI, middleware and other resources like Vault.
+
+- Run these command on the primary server that is running the UI and middleware software in Docker.
+- Copy the read token to a temp file to copy it to the worker server.
+- Make note of the LAN IP address of the primary server. It is needed for the GOLEM_VAULT_HOST and GOLEM_VAULT_HOST variables.
+- Make sure ports for RabbitMQ and Vault are open.
+
+```bash
+sudo more /var/lib/docker/volumes/spellbook-docker_vault_share/_data/read-token 
+ip address
+sudo ufw allow 5671
+sudo ufw allow 5672
+sudo ufw allow 8200
+```
+
+- Run these command on the server running the worker. The GOLEM_ID needs to be unique for every server and golem1 is used by the primary.
+- The first time you run the container it will timeout, git CTL + C or wait then copy the Vault token.
+```bash
+docker compose -f docker-compose-worker-nogpu.yml build
+GOLEM_VAULT_HOST=10.10.10.X GOLEM_AMQP_HOST=10.10.10.X GOLEM_ID=golem2 docker compose -f docker-compose-worker-nogpu.yml up
+sudo su
+echo "TOKEN FROM PRIMARY SERVER" > /var/lib/docker/volumes/spellbook-docker_vault_share/_data/read-token
+exit
+GOLEM_VAULT_HOST=10.10.10.X GOLEM_AMQP_HOST=10.10.10.X GOLEM_ID=golem2 docker compose -f docker-compose-worker-nogpu.yml up
 ```
 
 ### Nvidia Driver Installation
@@ -71,9 +114,17 @@ sudo systemctl restart docker
 sudo docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi
 ```
 
-### Build and Start Containers
+### Build and Start Containers (Nvidia GPU)
 
 ```bash
 docker compose build
 docker compose up
 ```
+
+### Build and Start Additional Workers (Nvidia GPU)
+
+Follow the directions under the *Build and Start Additional Workers (No GPU)* section substituting the build and up lines for the ones found below.
+```bash
+docker compose -f docker-compose-worker.yml build
+GOLEM_VAULT_HOST=10.10.10.X GOLEM_AMQP_HOST=10.10.10.X GOLEM_ID=golem2 docker compose -f docker-compose-worker.yml up
+```

arcane-bridge/Dockerfile

@@ -15,14 +15,13 @@ RUN mkdir -p /etc/apt/keyrings && \
 RUN groupadd -r arcane && useradd -r -m -g arcane arcane && \
     mkdir -p /app && chown arcane:arcane /app
 WORKDIR /app
-RUN echo "Installing 0.1.0 of Arcane Bridge"
-RUN git clone https://github.com/noco-ai/arcane-bridge.git /app
+RUN echo "Installing 0.2.0 of Arcane Bridge"
+RUN git clone --depth 1 --branch v0.2.0 https://github.com/noco-ai/arcane-bridge.git /app
 RUN chown -R arcane:arcane /app
 ENV NPM_CONFIG_PREFIX=/app/.npm-global
 ENV PATH=$PATH:/app/.npm-global/bin
 USER arcane
 RUN npm install && npm run compile
-
-CMD ["npm", "run", "start", "--", "-vh", "http://10.23.82.2:8200", "-vt", "/vault_share/write-token"]
+CMD ["npm", "run", "start", "--", "-vh", "http://10.23.82.2:8200", "-vt", "/vault_share/write-token", "-cs"]
 # CMD tail -f /dev/null
 # npm run start -- -vh http://10.23.82.2:8200 -vt /vault_share/write-token

docker-compose-nogpu.yml

@@ -0,0 +1,111 @@
+version: "3.8"
+
+services:
+  vault:
+    build:
+      dockerfile: vault/Dockerfile
+    container_name: spellbook_vault
+    ports:
+      - "8200:8200"
+    environment:
+      VAULT_ADDR: http://0.0.0.0:8200
+    volumes:
+      - vault_share:/vault_share
+    cap_add:
+      - IPC_LOCK
+    networks:
+      spellbook-net:
+        ipv4_address: 10.23.82.2
+
+  mariadb:
+    build:
+      dockerfile: mariadb/Dockerfile
+    container_name: spellbook_mariadb
+    environment:
+      MARIADB_ROOT_PASSWORD: "spellBOOK.temp.321"
+      MARIADB_DATABASE: "spellbook"
+    volumes:
+      - vault_share:/vault_share
+    ports:
+      - "3306:3306"
+    depends_on:
+      - vault
+    networks:
+      spellbook-net:
+        ipv4_address: 10.23.82.3
+
+  spellbook_ui:
+    build:
+      dockerfile: spellbook/Dockerfile
+    container_name: spellbook_ui
+    volumes:
+      - vault_share:/vault_share
+    ports:
+      - "4200:4200"
+    depends_on:
+      - vault
+      - mariadb
+      - rabbitmq
+    networks:
+      spellbook-net:
+        ipv4_address: 10.23.82.6
+
+  arcane_bridge:
+    build:
+      dockerfile: arcane-bridge/Dockerfile
+    container_name: spellbook_arcane_bridge
+    volumes:
+      - vault_share:/vault_share
+    ports:
+      - "3000:3000"
+    depends_on:
+      - vault
+      - mariadb
+      - rabbitmq
+    networks:
+      spellbook-net:
+        ipv4_address: 10.23.82.7
+
+  golem:
+    build:
+      dockerfile: elemental-golem/Dockerfile-nogpu      
+    container_name: spellbook_golem
+    environment:
+      - GOLEM_ID=${GOLEM_ID}
+      - GOLEM_AMQP_HOST=${GOLEM_AMQP_HOST}
+      - GOLEM_VAULT_HOST=${GOLEM_VAULT_HOST}
+    volumes:
+      - vault_share:/vault_share
+      - models_share:/server/data
+    depends_on:
+      - vault
+      - rabbitmq    
+    networks:
+      spellbook-net:
+        ipv4_address: 10.23.82.5
+
+  rabbitmq:
+    build:
+      dockerfile: rabbitmq/Dockerfile
+    container_name: spellbook_rabbitmq
+    depends_on:
+      - vault
+    ports:
+      - "15672:15672"
+      - "5672:5672"
+      - "5671:5671"
+    volumes:
+      - vault_share:/vault_share
+    networks:
+      spellbook-net:
+        ipv4_address: 10.23.82.4
+
+volumes:
+  vault_share:
+  models_share:
+
+networks:
+  spellbook-net:
+    ipam:
+      config:
+        - subnet: 10.23.82.0/16

docker-compose-worker-nogpu.yml

@@ -0,0 +1,28 @@
+version: "3.8"
+
+services:
+
+  golem:
+    build:
+      dockerfile: elemental-golem/Dockerfile-nogpu      
+    container_name: spellbook_golem_nogpu
+    volumes:
+      - vault_share:/vault_share
+      - models_share:/server/data    
+    environment:
+      - GOLEM_ID=${GOLEM_ID}
+      - GOLEM_AMQP_HOST=${GOLEM_AMQP_HOST}
+      - GOLEM_VAULT_HOST=${GOLEM_VAULT_HOST}
+    networks:
+      spellbook-net:
+        ipv4_address: 10.23.82.5
+
+volumes:
+  vault_share:
+  models_share:
+
+networks:
+  spellbook-net:
+    ipam:
+      config:
+        - subnet: 10.23.82.0/16

docker-compose-worker.yml

@@ -0,0 +1,35 @@
+version: "3.8"
+
+services:
+
+  golem:
+    build:
+      dockerfile: elemental-golem/Dockerfile      
+    container_name: spellbook_golem    
+    volumes:
+      - vault_share:/vault_share
+      - models_share:/server/data
+    environment:
+      - GOLEM_ID=${GOLEM_ID}
+      - GOLEM_AMQP_HOST=${GOLEM_AMQP_HOST}
+      - GOLEM_VAULT_HOST=${GOLEM_VAULT_HOST}
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    networks:
+      spellbook-net:
+        ipv4_address: 10.23.82.5
+
+volumes:
+  vault_share:
+  models_share:
+
+networks:
+  spellbook-net:
+    ipam:
+      config:
+        - subnet: 10.23.82.0/16

docker-compose.yml

@@ -1,5 +1,5 @@
 version: "3.8"
-
+      
 services:
   vault:
     build:
@@ -68,11 +68,15 @@ services:
 
   golem:
     build:
-      dockerfile: elemental-golem/Dockerfile
-    container_name: spellbook_golem
+      dockerfile: elemental-golem/Dockerfile      
+    container_name: spellbook_golem    
     volumes:
       - vault_share:/vault_share
       - models_share:/server/data
+    environment:
+      - GOLEM_ID=${GOLEM_ID}
+      - GOLEM_AMQP_HOST=${GOLEM_AMQP_HOST}
+      - GOLEM_VAULT_HOST=${GOLEM_VAULT_HOST}
     depends_on:
       - vault
       - rabbitmq
@@ -95,6 +99,8 @@ services:
       - vault
     ports:
       - "15672:15672"
+      - "5672:5672"
+      - "5671:5671"
     volumes:
       - vault_share:/vault_share
     networks:

elemental-golem/Dockerfile

@@ -13,11 +13,11 @@ ENV LLAMA_CUBLAS=1
 RUN groupadd -r golem && useradd -r -m -g golem golem && mkdir /server && chown -R golem:golem /server
 RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings starlette-context
 RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
-RUN echo "Installing v0.1.0 of Elemental Golem"
-RUN git clone https://github.com/noco-ai/elemental-golem.git /server
+RUN echo "Installing v0.2.1 of Elemental Golem"
+RUN git clone --depth 1 --branch v0.2.1 https://github.com/noco-ai/elemental-golem.git /server
 RUN pip install -r /server/requirements.txt
 RUN mkdir -p /server/data/loras/
 WORKDIR /server
-CMD ["python3", "server.py", "--server-id", "golem1", "--vault-host", "http://10.23.82.2:8200", "--vault-token-file", "/vault_share/read-token", "--vault-root", "spellbook", "--shared-models", "true"]
+CMD python3 server.py --server-id $GOLEM_ID --amqp-ip $GOLEM_AMQP_HOST --vault-host $GOLEM_VAULT_HOST --vault-token-file /vault_share/read-token --vault-root spellbook --shared-models true
 # CMD tail -f /dev/null
 # python3 server.py --server-id golem1 --vault-host http://10.23.82.2:8200 --vault-token-file /vault_share/read-token --vault-root spellbook --shared-models true

elemental-golem/Dockerfile-nogpu

@@ -0,0 +1,20 @@
+FROM ubuntu:22.04
+
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y git build-essential \
+    python3 python3-pip gcc tar wget \
+    ocl-icd-opencl-dev opencl-headers clinfo    
+
+COPY . .
+RUN groupadd -r golem && useradd -r -m -g golem golem && mkdir /server && chown -R golem:golem /server
+RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings starlette-context
+RUN pip install llama-cpp-python
+RUN echo "Installing v0.2.1 of Elemental Golem"
+RUN git clone --depth 1 --branch v0.2.1 https://github.com/noco-ai/elemental-golem.git /server
+RUN pip install -r /server/requirements-nogpu.txt
+RUN mkdir -p /server/data/loras/
+WORKDIR /server
+CMD python3 server.py --server-id $GOLEM_ID --amqp-ip $GOLEM_AMQP_HOST --vault-host $GOLEM_VAULT_HOST --vault-token-file /vault_share/read-token --vault-root spellbook --shared-models true --gpu-type nogpu
+# CMD tail -f /dev/null
+# python3 server.py --server-id golem1 --vault-host http://10.23.82.2:8200 --vault-token-file /vault_share/read-token --vault-root spellbook --shared-models true
+#CMD ["python3", "server.py", "--server-id", "$GOLEM_ID", "--amqp-ip", "$AMQP_IP", "--vault-host", "$VAULT_HOST", "--vault-token-file", "/vault_share/read-token", "--vault-root", "spellbook", "--shared-models", "true", "--gpu-type", "nogpu"]

mariadb/spellbook.sql

@@ -43,15 +43,20 @@ DROP TABLE IF EXISTS `chat_conversation`;
 /*!40101 SET character_set_client = utf8 */;
 CREATE TABLE `chat_conversation` (
   `id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+  `user_id` int(10) unsigned NOT NULL,
   `is_private` tinyint(1) NOT NULL,
   `is_shared` tinyint(1) NOT NULL,
   `system_message` text COLLATE utf8mb4_unicode_ci,
   `use_model` varchar(255) COLLATE utf8mb4_unicode_ci DEFAULT NULL,
   `topic` varchar(255) COLLATE utf8mb4_unicode_ci DEFAULT NULL,
-  `seed` int(10) DEFAULT '-1',
+  `seed` bigint(10) DEFAULT '-1',
   `temperature` float DEFAULT '1',
-  `top_k` float DEFAULT '0.9',
+  `top_k` int(10) DEFAULT 50,
   `top_p` float DEFAULT '0.9',
+  `min_p` float DEFAULT '0.05',
+  `mirostat` int(10) DEFAULT 0,
+  `mirostat_tau` float DEFAULT '5.0',
+  `mirostat_eta` float DEFAULT '0.1',
   `created_at` datetime NOT NULL,
   `updated_at` datetime NOT NULL,
   `locked` int(10) unsigned DEFAULT '0',
@@ -65,6 +70,7 @@ DROP TABLE IF EXISTS `chat_conversation_message`;
 /*!40101 SET character_set_client = utf8 */;
 CREATE TABLE `chat_conversation_message` (
   `id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+  `user_id` int(10) unsigned NOT NULL,
   `content` text COLLATE utf8mb4_unicode_ci NOT NULL,
   `role` varchar(255) COLLATE utf8mb4_unicode_ci NOT NULL,
   `conversation_id` int(10) unsigned NOT NULL,

spellbook/Dockerfile

@@ -9,8 +9,8 @@ RUN echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesourc
 RUN apt-get update
 RUN apt-get install nodejs -y
 RUN npm install -g @angular/cli@latest
-RUN echo "Install v0.1.0 of Spellbook UI"
-RUN git clone https://github.com/noco-ai/spellbook-ui.git /app
+RUN echo "Install v0.2.0 of Spellbook UI"
+RUN git clone --depth 1 --branch v0.2.0 https://github.com/noco-ai/spellbook-ui.git /app
 WORKDIR /app
 RUN npm install
 ADD spellbook/environment.ts /app/environments/environment.ts