lightspeed-stack/run.yaml at main · major/lightspeed-stack · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
version: '2'
image_name: minimal-viable-llama-stack-configuration

apis:
  - agents
  - datasetio
  - eval
  - files
  - inference
  - post_training
  - safety
  - scoring
  - telemetry
  - tool_runtime
  - vector_io
benchmarks: []
container_image: null
datasets: []
external_providers_dir: null
inference_store:
  db_path: .llama/distributions/ollama/inference_store.db
  type: sqlite
logging: null
metadata_store:
  db_path: .llama/distributions/ollama/registry.db
  namespace: null
  type: sqlite
providers:
  files:
  - provider_id: localfs
    provider_type: inline::localfs
    config:
      storage_dir: /tmp/llama-stack-files
      metadata_store:
        type: sqlite
        db_path: .llama/distributions/ollama/files_metadata.db
  agents:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      persistence_store:
        db_path: .llama/distributions/ollama/agents_store.db
        namespace: null
        type: sqlite
      responses_store:
        db_path: .llama/distributions/ollama/responses_store.db
        type: sqlite
  datasetio:
  - provider_id: huggingface
    provider_type: remote::huggingface
    config:
      kvstore:
        db_path: .llama/distributions/ollama/huggingface_datasetio.db
        namespace: null
        type: sqlite
  - provider_id: localfs
    provider_type: inline::localfs
    config:
      kvstore:
        db_path: .llama/distributions/ollama/localfs_datasetio.db
        namespace: null
        type: sqlite
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      kvstore:
        db_path: .llama/distributions/ollama/meta_reference_eval.db
        namespace: null
        type: sqlite
  inference:
    - provider_id: sentence-transformers # Can be any embedding provider
      provider_type: inline::sentence-transformers
      config: {}
    - provider_id: openai
      provider_type: remote::openai
      config:
        api_key: ${env.OPENAI_API_KEY}
  post_training:
  - provider_id: huggingface
    provider_type: inline::huggingface-gpu
    config:
      checkpoint_format: huggingface
      device: cpu
      distributed_backend: null
      dpo_output_dir: "."
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config:
      excluded_categories: []
  scoring:
  - provider_id: basic
    provider_type: inline::basic
    config: {}
  - provider_id: llm-as-judge
    provider_type: inline::llm-as-judge
    config: {}
  - provider_id: braintrust
    provider_type: inline::braintrust
    config:
      openai_api_key: '********'
  telemetry:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      service_name: 'lightspeed-stack-telemetry'
      sinks: sqlite
      sqlite_db_path: .llama/distributions/ollama/trace_store.db
  tool_runtime:
    - provider_id: model-context-protocol
      provider_type: remote::model-context-protocol
      config: {}
    - provider_id: rag-runtime
      provider_type: inline::rag-runtime
      config: {}
  vector_io:
  - provider_id: faiss
    provider_type: inline::faiss # Or preferred vector DB
    config:
      kvstore:
        db_path: .llama/distributions/ollama/faiss_store.db # Location of vector database
        namespace: null
        type: sqlite
scoring_fns: []
server:
  auth: null
  host: null
  port: 8321
  quota: null
  tls_cafile: null
  tls_certfile: null
  tls_keyfile: null
shields:
  - shield_id: llama-guard-shield
    provider_id: llama-guard
    provider_shield_id: "gpt-3.5-turbo"  # Model to use for safety checks
vector_dbs:
  - vector_db_id: my_knowledge_base
    embedding_model: sentence-transformers/all-mpnet-base-v2
    embedding_dimension: 768
    provider_id: faiss
models:
  - model_id: sentence-transformers/all-mpnet-base-v2 # Example embedding model
    model_type: embedding
    provider_id: sentence-transformers
    provider_model_id: sentence-transformers/all-mpnet-base-v2 # Location of embedding model
    metadata:
      embedding_dimension: 768 # Depends on chosen model
  - model_id: gpt-4-turbo
    model_type: llm
    provider_id: openai
    provider_model_id: gpt-4-turbo

tool_groups:
  - toolgroup_id: builtin::rag
    provider_id: rag-runtime