fix: Bare metal (bionic-gpt#409)

Seniaxz · Mar 19, 2024 · e4424e3 · e4424e3
1 parent a5b04d8
commit e4424e3
Show file tree

Hide file tree

Showing 18 changed files with 92 additions and 676 deletions.
diff --git a/README.md b/README.md
@@ -93,8 +93,30 @@
 
 See the [open issues](https://github.com/purton-tech/bionicgpt/issues) for a full list of proposed features (and known issues).
 
+# Enterprise
+For companies that need better security, user management and professional support
+
+[Talk to the founders](https://calendly.com/bionicgpt)
+
+This covers: 
+- ✅ **Help with integrations**
+- ✅ **Feature Prioritization**
+- ✅ **Custom Integrations**
+- ✅ **LTS (Long Term Support) Versions**
+- ✅ **Professional Support**
+- ✅ **Custom SLAs**
+- ✅ **Secure access with Single Sign-On**
+- ✅ **Continuous Batching**
+- ✅ **Data Pipelines**
+
+# Support / talk with founders
+
+- [Schedule a Chat 👋](https://calendly.com/bionicgpt)
+- [Connect on Linked in 💭](https://www.linkedin.com/in/kulbinderdio/)
+- Our emails ✉️ ian@bionic-gpt.com / dio@bionic-gpt.com
+
 <!-- Try it out -->
-## Try it out with `docker compose`
+## Try it out
 
 follow [our guide](https://bionic-gpt.com/docs/running-locally/introduction/) to running Bionic-GPT on your local machine.
 

diff --git a/crates/ui-pages/team_members/team_role.rs b/crates/ui-pages/team_members/team_role.rs
@@ -10,14 +10,14 @@ pub fn Role(cx: Scope, role: Role) -> Element {
             Label {
                 class: "mr-2",
                 label_role: LabelRole::Highlight,
-                "SystemAdministrator"
+                "System Administrator"
             }
         )),
         Role::TeamManager => cx.render(rsx!(
             Label {
                 class: "mr-2",
                 label_role: LabelRole::Neutral,
-                "Team Manger"
+                "Team Manager"
             }
         )),
         Role::Collaborator => cx.render(rsx!(

diff --git a/install.sh b/install.sh
@@ -32,6 +32,7 @@ reset_k3s() {
     sudo /usr/local/bin/k3s-uninstall.sh
     curl -sfL https://get.k3s.io | sh -
     sudo chmod 444 /etc/rancher/k3s/k3s.yaml
+    mkdir -p ~/.kube
     cp /etc/rancher/k3s/k3s.yaml ~/.kube/config
     sed -i "s,127.0.0.1,$1,g" ~/.kube/config
 }

diff --git a/website/content/.spelling b/website/content/.spelling
@@ -183,6 +183,10 @@ Airbyte
 localhost
 RabbitMQ
 MQ
+Ollama
+systemd
+K3s
+IoT
  - docs/rag/generating-embeddings.md
 80
 Instruction-Finetuned

diff --git a/website/content/docs/enterprise-edition/adding-models.md b/website/content/docs/enterprise-edition/adding-models.md
@@ -1,54 +1,42 @@
 +++
-title = "Adding LLM Models"
+title = "Connecting to Ollama"
 weight = 95
 sort_by = "weight"
 +++
 
-To add a model to your cluster you can create a [Deployment](https://kubernetes.io/docs/concepts/workloads/controllers/deployment/) and a [Service](https://kubernetes.io/docs/concepts/services-networking/service/).
-
-## Example Adding Mixtral 8x7B (Work in progress)
-
-This section is a work in progress but deploying a new model will look something like this.
-
-```yml
-apiVersion: v1
-kind: Service
-metadata:
-  name: mixtral-8x7b
-  namespace: bionic-gpt
-spec:
-  selector:
-    app: mixtral-8x7b
-  ports:
-    - protocol: TCP
-      port: 8000
-      targetPort: 8000
-
----
-
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: mixtral-8x7b-deployment
-  namespace: bionic-gpt
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: mixtral-8x7b
-  template:
-    metadata:
-      labels:
-        app: mixtral-8x7b
-    spec:
-      containers:
-      - name: bionic-gpt-operator
-        image: ghcr.io/huggingface/text-generation-inference:sha-0eabc83
-        args: 
-          - --model-id 
-          - mistralai/Mixtral-8x7B-Instruct-v0.1
-          - --quantize 
-          - gptq
+We need to get Ollama to listen on `0.0.0.0`.
+
+Edit the systemd service by calling `sudo vi /etc/systemd/system/ollama.service`. This will open an editor.
+
+For each environment variable, add a line Environment under section [Service]:
+
+```
+[Service]
+Environment="OLLAMA_HOST=0.0.0.0"
+```
+
+Save and exit.
+
+Reload systemd and restart Ollama:
+
+```sh
+systemctl daemon-reload
+systemctl restart ollama
+```
+
+You can run the following to view the logs
+
 ```
+journalctl -u ollama
+```
+
+## Test Ollama
+
+Get you host with `hostname` then curl using that host.
 
-The model and inference engine must run in the same container.
+```sh
+curl http://pop-os:11434/api/generate -d '{
+  "model": "phi",
+  "prompt":"Why is the sky blue?"
+}'
+```
diff --git a/website/content/docs/enterprise-edition/install-bionic-operator.md b/website/content/docs/enterprise-edition/install-bionic-operator.md