Add BrainForge LLM Service Deployment option

neon_diana_utils/configuration.py

@@ -171,6 +171,27 @@ def make_keys_config(write_config: bool,
             config_confirmed = \
                 click.confirm("Is this configuration correct?")
 
+    brainforge_config = {"clients": {}}
+    if click.confirm("Configure BrainForge LLMs?"):
+        hosts_complete = False
+        while not hosts_complete:
+            name = click.prompt("vLLM Endpoint Name", type=str)
+            url = click.prompt("vLLM URL", type=str)
+            key = click.prompt("vLLM API key", type=str)
+            client_config = {name: {"api_url": url, "api_key": key}}
+            click.echo(pformat(client_config))
+            if click.confirm("Is this configuration correct?"):
+                brainforge_config["clients"][name] = client_config[name]
+            if not click.confirm("Add another client?"):
+                hosts_complete = True
+        confirmed = False
+        while not confirmed:
+            hf_token = click.prompt("HuggingFace Token", type=str)
+            brainforge_config['hf_token'] = hf_token
+            click.echo(brainforge_config)
+            if click.confirm("Is this configuration correct?"):
+                confirmed = True
+
     chatgpt_config = dict()
     if click.confirm("Configure ChatGPT LLM?"):
         config_confirmed = False
@@ -371,7 +392,8 @@ def make_keys_config(write_config: bool,
             "aggregators": {
                 "sentry": sentry_sdk_config,
             }
-        }
+        },
+        "brainforge_llm_service": brainforge_config
     }
     if write_config:
         click.echo(f"Writing configuration to {output_file}")
@@ -649,6 +671,7 @@ def _get_unconfigured_mq_backend_services(config: dict) -> Set[str]:
     config_to_service = {'api_services': 'neon-api-proxy',
                          'keys.emails': 'neon-email-proxy',
                          'keys.track_my_brands': 'neon-brands-service',
+                         'brainforge_llm_service': 'brainforge-llm-service',
                          'LLM_CHAT_GPT': 'neon-llm-chatgpt',
                          'LLM_VLLM': 'neon-llm-vllm',
                          'LLM_FASTCHAT': 'neon-llm-fastchat',
@@ -747,7 +770,8 @@ def configure_backend(username: str = None,
         else:
             # Define a default value so secret can be generated
             encoded_token = get_github_encoded_auth("", "")
-            to_disable = ['neon-brands-service', 'neon-script-parser']
+            to_disable = ['neon-brands-service', 'neon-script-parser',
+                          'brainforge-llm-service']
             disabled_mq_services += to_disable
         confirmed = False
         email = ''
@@ -805,6 +829,8 @@ def configure_backend(username: str = None,
         diana_config = join(output_path, "xdg", "config", "neon", "diana.yaml")
     else:
         raise RuntimeError(f"{orchestrator} is not yet supported")
+
+    # Generate configuration for required core services
     try:
         # Generate RabbitMQ config
         username = username or click.prompt("RabbitMQ Admin Username", type=str)

neon_diana_utils/helm_charts/backend/diana-backend/Chart.yaml

@@ -15,7 +15,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.1.30
+version: 0.1.31
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
@@ -35,5 +35,5 @@ dependencies:
     version: 0.0.15
     repository: file://../http-services
   - name: diana-mq
-    version: 0.0.19
+    version: 0.0.20
     repository: file://../mq-services

neon_diana_utils/helm_charts/backend/mq-services/Chart.yaml

@@ -3,7 +3,7 @@ name: diana-mq
 description: Deploy DIANA MQ Services
 
 type: application
-version: 0.0.19
+version: 0.0.20
 appVersion: "1.0.1a31"
 dependencies:
   - name: neon-api-proxy
@@ -30,6 +30,10 @@ dependencies:
     alias: neon-users-service
     version: 0.0.1
     repository: file://../../mq/neon-users-service
+  - name: brainforge-llm-service
+    alias: brainforge-llm-service
+    version: 0.0.1
+    repository: file://../../mq/brainforge-llm-service
   - name: neon-llm-chatgpt
     alias: neon-llm-chatgpt
     version: 0.0.7

neon_diana_utils/helm_charts/backend/mq-services/values.yaml

@@ -18,6 +18,9 @@ neon-script-parser:
 neon-users-service:
   image:
     tag: *tag
+brainforge-llm-service:
+  image:
+    tag: *tag
 neon-llm-chatgpt:
   image:
     tag: *tag

neon_diana_utils/helm_charts/mq/brainforge-llm-service/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

neon_diana_utils/helm_charts/mq/brainforge-llm-service/Chart.yaml

@@ -0,0 +1,12 @@
+apiVersion: v2
+name: brainforge-llm-service
+description: Deploy a Brainforge LLM Backend Service
+
+type: application
+version: 0.0.1
+appVersion: "1.0.1a29"
+
+dependencies:
+  - name: base-mq
+    version: 0.0.10
+    repository: file://../../base/base-mq

neon_diana_utils/helm_charts/mq/brainforge-llm-service/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "brainforge-llm-service.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "brainforge-llm-service.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "brainforge-llm-service.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "brainforge-llm-service.labels" -}}
+helm.sh/chart: {{ include "brainforge-llm-service.chart" . }}
+{{ include "brainforge-llm-service.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "brainforge-llm-service.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "brainforge-llm-service.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "brainforge-llm-service.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "brainforge-llm-service.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

neon_diana_utils/helm_charts/mq/brainforge-llm-service/templates/deployment.yaml

@@ -0,0 +1 @@
+{{- include "base-mq.deployment" .}}

neon_diana_utils/helm_charts/mq/brainforge-llm-service/templates/service.yaml

@@ -0,0 +1 @@
+{{- include "base-mq.service" .}}

neon_diana_utils/helm_charts/mq/brainforge-llm-service/values.yaml

@@ -0,0 +1,12 @@
+serviceName: backend-mq-brainforge-llm
+replicaCount: 1
+configSecret: diana-config
+image:
+  pullSecret: github-auth
+  repository: ghcr.io/neongeckocom/brainforge-llm-service
+  pullPolicy: Always
+  tag: dev
+resources:
+  requests:
+    memory: "500Mi"
+    cpu: "1.0"

neon_diana_utils/templates/backend/Chart.yaml

@@ -8,5 +8,5 @@ appVersion: "1.0.1a5"
 
 dependencies:
   - name: backend
-    version: 0.1.30
+    version: 0.1.31
     repository: https://neongeckocom.github.io/neon-diana-utils

neon_diana_utils/templates/backend/values.yaml

@@ -25,5 +25,7 @@ backend:
       image: {}
     neon-users-service:
       image: {}
+    brainforge-llm-service:
+      image: {}
   letsencrypt:
     server: https://acme-v02.api.letsencrypt.org/directory

neon_diana_utils/templates/mq_user_mapping.yml

@@ -29,6 +29,8 @@ neon_core:
   - chat_api_proxy
 chat_observer:
   - chat_observer
+brainforge_llm_service:
+  - brainforge_llm_service
 neon_llm_submind:
   - neon_llm_submind
 neon_bot_submind:

neon_diana_utils/templates/rmq_backend_config.yml

@@ -93,6 +93,11 @@ users:
     password:
     tags:
       - chatbots
+  - name: "brainforge_llm_service"
+    password:
+    tags:
+      - backend
+      - llm
 vhosts:
   - name: "/neon_emails"
   - name: "/neon_api"
@@ -105,6 +110,7 @@ vhosts:
   - name: "/neon_chat_api"
   - name: "/chatbots"
   - name: "/neon_users"
+  - name: "/brainforge"
 permissions:
   - user: "neon_core"
     vhost: "/neon_chat_api"
@@ -258,3 +264,13 @@ permissions:
     configure: ".*"
     write: ".*"
     read: ".*"
+  - user: "neon_api_utils"
+    vhost: "/brainforge"
+    configure: "./*"
+    write: "./*"
+    read: "./*"
+  - user: "brainforge_llm_service"
+    vhost: "/brainforge"
+    configure: "./*"
+    write: "./*"
+    read: "./*"