DEVOCEAN

helm repo add go-skynet https://go-skynet.github.io/helm-charts/

cat <<EOF > values.yaml
replicaCount: 1

deployment:
  image: quay.io/go-skynet/local-ai:latest
  env:
    threads: 4
    context_size: 512
  modelsPath: "/models"

resources:
  {}
  # We usually recommend not to specify default resources and to leave this as a conscious
  # choice for the user. This also increases chances charts run on environments with little
  # resources, such as Minikube. If you do want to specify resources, uncomment the following
  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
  # limits:
  #   cpu: 100m
  #   memory: 128Mi
  # requests:
  #   cpu: 100m
  #   memory: 128Mi

# Prompt templates to include
# Note: the keys of this map will be the names of the prompt template files
promptTemplates:
  {}
  # ggml-gpt4all-j.tmpl: |
  #   The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
  #   ### Prompt:
  #   {{.Input}}
  #   ### Response:

# Models to download at runtime
models:
  # Whether to force download models even if they already exist
  forceDownload: false

  # The list of URLs to download models from
  # Note: the name of the file will be the name of the loaded model
  list:
    - url: "https://gpt4all.io/models/gguf/gpt4all-falcon-newbpe-q4_0.gguf"
      # basicAuth: base64EncodedCredentials

  # Persistent storage for models and prompt templates.
  # PVC and HostPath are mutually exclusive. If both are enabled,
  # PVC configuration takes precedence. If neither are enabled, ephemeral
  # storage is used.
  persistence:
    pvc:
      enabled: false
      size: 6Gi
      accessModes:
        - ReadWriteOnce

      annotations: {}

      # Optional
      storageClass: ~

    hostPath:
      enabled: false
      path: "/models"

service:
  type: ClusterIP
  port: 80
  annotations: {}
  # If using an AWS load balancer, you'll need to override the default 60s load balancer idle timeout
  # service.beta.kubernetes.io/aws-load-balancer-connection-idle-timeout: "1200"

ingress:
  enabled: false
  className: ""
  annotations:
    {}
    # kubernetes.io/ingress.class: nginx
    # kubernetes.io/tls-acme: "true"
  hosts:
    - host: chart-example.local
      paths:
        - path: /
          pathType: ImplementationSpecific
  tls: []
  #  - secretName: chart-example-tls
  #    hosts:
  #      - chart-example.local

nodeSelector: {}

tolerations: []

affinity: {}

EOF

helm install local-ai go-skynet/local-ai -f values.yaml

Defaulted container "local-ai" out of: local-ai, download-model (init)
@@@@@
Skipping rebuild
@@@@@
If you are experiencing issues with the pre-compiled builds, try setting REBUILD=true
If you are still experiencing issues with the build, try setting CMAKE_ARGS and disable the instructions set as needed:
CMAKE_ARGS="-DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF"
see the documentation at: https://localai.io/basics/build/index.html
Note: See also https://github.com/go-skynet/LocalAI/issues/288
@@@@@
CPU info:
model name      : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology n_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a rdseed adx smap intel_pt xsaveopt cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts
CPU:    AVX    found OK
CPU:    AVX2   found OK
CPU: no AVX512 found
@@@@@
11:58PM DBG no galleries to load
11:58PM INF Starting LocalAI using 4 threads, with models path: /models
11:58PM INF LocalAI version: v2.7.0 (abd678e147e29ab46a038d28c4806768b2b7cde5)
11:58PM INF Preloading models from /models

 ┌───────────────────────────────────────────────────┐
 │                   Fiber v2.50.0                   │
 │               http://127.0.0.1:8080               │
 │       (bound on host 0.0.0.0 and port 8080)       │
 │                                                   │
 │ Handlers ............ 73  Processes ........... 1 │
 │ Prefork ....... Disabled  PID ................ 14 │
 └───────────────────────────────────────────────────┘

12:01AM INF Trying to load the model 'gpt4all-falcon-newbpe-q4_0.gguf' with all the available backends: llama-cpp, llama-ggml, llama, gpt4all, gptneox, bert-embeddings, falcon-ggml, gptj, gpt2, dolly, mpt, replit, starcoder, rwkv, whisper, stablediffusion, tinydream, piper, /build/backend/python/exllama/run.sh, /build/backend/python/exllama2/run.sh, /build/backend/python/sentencetransformers/run.sh, /build/backend/python/mamba/run.sh, /build/backend/python/vall-e-x/run.sh, /build/backend/python/transformers-musicgen/run.sh, /build/backend/python/bark/run.sh, /build/backend/python/transformers/run.sh, /build/backend/python/autogptq/run.sh, /build/backend/python/diffusers/run.sh, /build/backend/python/coqui/run.sh, /build/backend/python/petals/run.sh, /build/backend/python/vllm/run.sh, /build/backend/python/sentencetransformers/run.sh
12:01AM INF [llama-cpp] Attempting to load
12:01AM INF Loading model 'gpt4all-falcon-newbpe-q4_0.gguf' with backend llama-cpp
12:01AM INF [llama-cpp] Loads OK

#LocalAI는 openAI에서 지원하는 API를 지원한다.
#LocalAI pod에 들어가서 하기와 같이 curl 명령어를 수행하면 된다.
#content에 원하는 질문을 넣으면 된다.
 
curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
   "model": "gpt4all-falcon-newbpe-q4_0.gguf",
     "messages": [{"role": "user", "content": "do you know k8s?"}],
     "temperature": 0.9
   }'