llama-stack 0.4.3__py3-none-any.whl → 0.5.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (311) hide show
  1. llama_stack/cli/stack/_list_deps.py +11 -7
  2. llama_stack/cli/stack/run.py +3 -25
  3. llama_stack/core/access_control/datatypes.py +78 -0
  4. llama_stack/core/configure.py +2 -2
  5. {llama_stack_api/internal → llama_stack/core/connectors}/__init__.py +2 -2
  6. llama_stack/core/connectors/connectors.py +162 -0
  7. llama_stack/core/conversations/conversations.py +61 -58
  8. llama_stack/core/datatypes.py +54 -8
  9. llama_stack/core/library_client.py +60 -13
  10. llama_stack/core/prompts/prompts.py +43 -42
  11. llama_stack/core/routers/datasets.py +20 -17
  12. llama_stack/core/routers/eval_scoring.py +143 -53
  13. llama_stack/core/routers/inference.py +20 -9
  14. llama_stack/core/routers/safety.py +30 -42
  15. llama_stack/core/routers/vector_io.py +15 -7
  16. llama_stack/core/routing_tables/models.py +42 -3
  17. llama_stack/core/routing_tables/scoring_functions.py +19 -19
  18. llama_stack/core/routing_tables/shields.py +20 -17
  19. llama_stack/core/routing_tables/vector_stores.py +8 -5
  20. llama_stack/core/server/auth.py +192 -17
  21. llama_stack/core/server/fastapi_router_registry.py +40 -5
  22. llama_stack/core/server/server.py +24 -5
  23. llama_stack/core/stack.py +54 -10
  24. llama_stack/core/storage/datatypes.py +9 -0
  25. llama_stack/core/store/registry.py +1 -1
  26. llama_stack/core/utils/exec.py +2 -2
  27. llama_stack/core/utils/type_inspection.py +16 -2
  28. llama_stack/distributions/dell/config.yaml +4 -1
  29. llama_stack/distributions/dell/doc_template.md +209 -0
  30. llama_stack/distributions/dell/run-with-safety.yaml +4 -1
  31. llama_stack/distributions/nvidia/config.yaml +4 -1
  32. llama_stack/distributions/nvidia/doc_template.md +170 -0
  33. llama_stack/distributions/nvidia/run-with-safety.yaml +4 -1
  34. llama_stack/distributions/oci/config.yaml +4 -1
  35. llama_stack/distributions/oci/doc_template.md +140 -0
  36. llama_stack/distributions/open-benchmark/config.yaml +9 -1
  37. llama_stack/distributions/postgres-demo/config.yaml +1 -1
  38. llama_stack/distributions/starter/build.yaml +62 -0
  39. llama_stack/distributions/starter/config.yaml +22 -3
  40. llama_stack/distributions/starter/run-with-postgres-store.yaml +22 -3
  41. llama_stack/distributions/starter/starter.py +13 -1
  42. llama_stack/distributions/starter-gpu/build.yaml +62 -0
  43. llama_stack/distributions/starter-gpu/config.yaml +22 -3
  44. llama_stack/distributions/starter-gpu/run-with-postgres-store.yaml +22 -3
  45. llama_stack/distributions/template.py +10 -2
  46. llama_stack/distributions/watsonx/config.yaml +4 -1
  47. llama_stack/log.py +1 -0
  48. llama_stack/models/llama/resources/dog.jpg +0 -0
  49. llama_stack/models/llama/resources/pasta.jpeg +0 -0
  50. llama_stack/models/llama/resources/small_dog.jpg +0 -0
  51. llama_stack/providers/inline/agents/meta_reference/__init__.py +1 -0
  52. llama_stack/providers/inline/agents/meta_reference/agents.py +58 -61
  53. llama_stack/providers/inline/agents/meta_reference/responses/openai_responses.py +187 -60
  54. llama_stack/providers/inline/agents/meta_reference/responses/streaming.py +99 -22
  55. llama_stack/providers/inline/agents/meta_reference/responses/types.py +2 -1
  56. llama_stack/providers/inline/agents/meta_reference/responses/utils.py +4 -1
  57. llama_stack/providers/inline/agents/meta_reference/safety.py +2 -2
  58. llama_stack/providers/inline/batches/reference/batches.py +2 -1
  59. llama_stack/providers/inline/eval/meta_reference/eval.py +40 -32
  60. llama_stack/providers/inline/ios/inference/LocalInferenceImpl/LocalInference.h +9 -0
  61. llama_stack/providers/inline/ios/inference/LocalInferenceImpl/LocalInference.swift +189 -0
  62. llama_stack/providers/inline/ios/inference/LocalInferenceImpl/Parsing.swift +238 -0
  63. llama_stack/providers/inline/ios/inference/LocalInferenceImpl/PromptTemplate.swift +12 -0
  64. llama_stack/providers/inline/ios/inference/LocalInferenceImpl/SystemPrompts.swift +89 -0
  65. llama_stack/providers/inline/ios/inference/LocalInferenceImpl.xcodeproj/project.pbxproj +550 -0
  66. llama_stack/providers/inline/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/contents.xcworkspacedata +7 -0
  67. llama_stack/providers/inline/ios/inference/LocalInferenceImpl.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist +8 -0
  68. llama_stack/providers/inline/post_training/huggingface/post_training.py +33 -38
  69. llama_stack/providers/inline/post_training/huggingface/utils.py +2 -5
  70. llama_stack/providers/inline/post_training/torchtune/common/utils.py +5 -9
  71. llama_stack/providers/inline/post_training/torchtune/post_training.py +28 -33
  72. llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py +2 -4
  73. llama_stack/providers/inline/safety/code_scanner/code_scanner.py +12 -15
  74. llama_stack/providers/inline/safety/llama_guard/llama_guard.py +20 -24
  75. llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py +11 -17
  76. llama_stack/providers/inline/scoring/basic/scoring.py +13 -17
  77. llama_stack/providers/inline/scoring/braintrust/braintrust.py +15 -15
  78. llama_stack/providers/inline/scoring/llm_as_judge/scoring.py +13 -17
  79. llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py +1 -1
  80. llama_stack/providers/registry/agents.py +1 -0
  81. llama_stack/providers/registry/inference.py +1 -9
  82. llama_stack/providers/registry/vector_io.py +136 -16
  83. llama_stack/providers/remote/datasetio/nvidia/README.md +74 -0
  84. llama_stack/providers/remote/eval/nvidia/README.md +134 -0
  85. llama_stack/providers/remote/eval/nvidia/eval.py +22 -21
  86. llama_stack/providers/remote/files/s3/README.md +266 -0
  87. llama_stack/providers/remote/files/s3/config.py +5 -3
  88. llama_stack/providers/remote/files/s3/files.py +2 -2
  89. llama_stack/providers/remote/inference/gemini/gemini.py +4 -0
  90. llama_stack/providers/remote/inference/nvidia/NVIDIA.md +203 -0
  91. llama_stack/providers/remote/inference/openai/openai.py +2 -0
  92. llama_stack/providers/remote/inference/together/together.py +4 -0
  93. llama_stack/providers/remote/inference/vertexai/config.py +3 -3
  94. llama_stack/providers/remote/inference/vertexai/vertexai.py +5 -2
  95. llama_stack/providers/remote/inference/vllm/config.py +37 -18
  96. llama_stack/providers/remote/inference/vllm/vllm.py +0 -3
  97. llama_stack/providers/remote/inference/watsonx/watsonx.py +4 -0
  98. llama_stack/providers/remote/post_training/nvidia/README.md +151 -0
  99. llama_stack/providers/remote/post_training/nvidia/models.py +3 -11
  100. llama_stack/providers/remote/post_training/nvidia/post_training.py +31 -33
  101. llama_stack/providers/remote/safety/bedrock/bedrock.py +10 -27
  102. llama_stack/providers/remote/safety/nvidia/README.md +78 -0
  103. llama_stack/providers/remote/safety/nvidia/nvidia.py +9 -25
  104. llama_stack/providers/remote/safety/sambanova/sambanova.py +13 -11
  105. llama_stack/providers/remote/vector_io/elasticsearch/__init__.py +17 -0
  106. llama_stack/providers/remote/vector_io/elasticsearch/config.py +32 -0
  107. llama_stack/providers/remote/vector_io/elasticsearch/elasticsearch.py +463 -0
  108. llama_stack/providers/remote/vector_io/oci/__init__.py +22 -0
  109. llama_stack/providers/remote/vector_io/oci/config.py +41 -0
  110. llama_stack/providers/remote/vector_io/oci/oci26ai.py +595 -0
  111. llama_stack/providers/remote/vector_io/pgvector/config.py +69 -2
  112. llama_stack/providers/remote/vector_io/pgvector/pgvector.py +255 -6
  113. llama_stack/providers/remote/vector_io/qdrant/qdrant.py +62 -38
  114. llama_stack/providers/utils/bedrock/client.py +3 -3
  115. llama_stack/providers/utils/bedrock/config.py +7 -7
  116. llama_stack/providers/utils/inference/__init__.py +0 -25
  117. llama_stack/providers/utils/inference/embedding_mixin.py +4 -0
  118. llama_stack/providers/utils/inference/http_client.py +239 -0
  119. llama_stack/providers/utils/inference/litellm_openai_mixin.py +6 -0
  120. llama_stack/providers/utils/inference/model_registry.py +148 -2
  121. llama_stack/providers/utils/inference/openai_compat.py +1 -158
  122. llama_stack/providers/utils/inference/openai_mixin.py +42 -2
  123. llama_stack/providers/utils/inference/prompt_adapter.py +0 -209
  124. llama_stack/providers/utils/memory/openai_vector_store_mixin.py +92 -5
  125. llama_stack/providers/utils/memory/vector_store.py +46 -19
  126. llama_stack/providers/utils/responses/responses_store.py +40 -6
  127. llama_stack/providers/utils/safety.py +114 -0
  128. llama_stack/providers/utils/tools/mcp.py +44 -3
  129. llama_stack/testing/api_recorder.py +9 -3
  130. {llama_stack-0.4.3.dist-info → llama_stack-0.5.0.dist-info}/METADATA +14 -2
  131. {llama_stack-0.4.3.dist-info → llama_stack-0.5.0.dist-info}/RECORD +135 -279
  132. llama_stack-0.5.0.dist-info/top_level.txt +1 -0
  133. llama_stack/distributions/meta-reference-gpu/__init__.py +0 -7
  134. llama_stack/distributions/meta-reference-gpu/config.yaml +0 -140
  135. llama_stack/distributions/meta-reference-gpu/meta_reference.py +0 -163
  136. llama_stack/distributions/meta-reference-gpu/run-with-safety.yaml +0 -155
  137. llama_stack/models/llama/hadamard_utils.py +0 -88
  138. llama_stack/models/llama/llama3/args.py +0 -74
  139. llama_stack/models/llama/llama3/generation.py +0 -378
  140. llama_stack/models/llama/llama3/model.py +0 -304
  141. llama_stack/models/llama/llama3/multimodal/__init__.py +0 -12
  142. llama_stack/models/llama/llama3/multimodal/encoder_utils.py +0 -180
  143. llama_stack/models/llama/llama3/multimodal/image_transform.py +0 -409
  144. llama_stack/models/llama/llama3/multimodal/model.py +0 -1430
  145. llama_stack/models/llama/llama3/multimodal/utils.py +0 -26
  146. llama_stack/models/llama/llama3/quantization/__init__.py +0 -5
  147. llama_stack/models/llama/llama3/quantization/loader.py +0 -316
  148. llama_stack/models/llama/llama3_1/__init__.py +0 -12
  149. llama_stack/models/llama/llama3_1/prompt_format.md +0 -358
  150. llama_stack/models/llama/llama3_1/prompts.py +0 -258
  151. llama_stack/models/llama/llama3_2/__init__.py +0 -5
  152. llama_stack/models/llama/llama3_2/prompts_text.py +0 -229
  153. llama_stack/models/llama/llama3_2/prompts_vision.py +0 -126
  154. llama_stack/models/llama/llama3_2/text_prompt_format.md +0 -286
  155. llama_stack/models/llama/llama3_2/vision_prompt_format.md +0 -141
  156. llama_stack/models/llama/llama3_3/__init__.py +0 -5
  157. llama_stack/models/llama/llama3_3/prompts.py +0 -259
  158. llama_stack/models/llama/llama4/args.py +0 -107
  159. llama_stack/models/llama/llama4/ffn.py +0 -58
  160. llama_stack/models/llama/llama4/moe.py +0 -214
  161. llama_stack/models/llama/llama4/preprocess.py +0 -435
  162. llama_stack/models/llama/llama4/quantization/__init__.py +0 -5
  163. llama_stack/models/llama/llama4/quantization/loader.py +0 -226
  164. llama_stack/models/llama/llama4/vision/__init__.py +0 -5
  165. llama_stack/models/llama/llama4/vision/embedding.py +0 -210
  166. llama_stack/models/llama/llama4/vision/encoder.py +0 -412
  167. llama_stack/models/llama/quantize_impls.py +0 -316
  168. llama_stack/providers/inline/inference/meta_reference/__init__.py +0 -20
  169. llama_stack/providers/inline/inference/meta_reference/common.py +0 -24
  170. llama_stack/providers/inline/inference/meta_reference/config.py +0 -68
  171. llama_stack/providers/inline/inference/meta_reference/generators.py +0 -201
  172. llama_stack/providers/inline/inference/meta_reference/inference.py +0 -542
  173. llama_stack/providers/inline/inference/meta_reference/model_parallel.py +0 -77
  174. llama_stack/providers/inline/inference/meta_reference/parallel_utils.py +0 -353
  175. llama_stack-0.4.3.dist-info/top_level.txt +0 -2
  176. llama_stack_api/__init__.py +0 -945
  177. llama_stack_api/admin/__init__.py +0 -45
  178. llama_stack_api/admin/api.py +0 -72
  179. llama_stack_api/admin/fastapi_routes.py +0 -117
  180. llama_stack_api/admin/models.py +0 -113
  181. llama_stack_api/agents.py +0 -173
  182. llama_stack_api/batches/__init__.py +0 -40
  183. llama_stack_api/batches/api.py +0 -53
  184. llama_stack_api/batches/fastapi_routes.py +0 -113
  185. llama_stack_api/batches/models.py +0 -78
  186. llama_stack_api/benchmarks/__init__.py +0 -43
  187. llama_stack_api/benchmarks/api.py +0 -39
  188. llama_stack_api/benchmarks/fastapi_routes.py +0 -109
  189. llama_stack_api/benchmarks/models.py +0 -109
  190. llama_stack_api/common/__init__.py +0 -5
  191. llama_stack_api/common/content_types.py +0 -101
  192. llama_stack_api/common/errors.py +0 -95
  193. llama_stack_api/common/job_types.py +0 -38
  194. llama_stack_api/common/responses.py +0 -77
  195. llama_stack_api/common/training_types.py +0 -47
  196. llama_stack_api/common/type_system.py +0 -146
  197. llama_stack_api/connectors.py +0 -146
  198. llama_stack_api/conversations.py +0 -270
  199. llama_stack_api/datasetio.py +0 -55
  200. llama_stack_api/datasets/__init__.py +0 -61
  201. llama_stack_api/datasets/api.py +0 -35
  202. llama_stack_api/datasets/fastapi_routes.py +0 -104
  203. llama_stack_api/datasets/models.py +0 -152
  204. llama_stack_api/datatypes.py +0 -373
  205. llama_stack_api/eval.py +0 -137
  206. llama_stack_api/file_processors/__init__.py +0 -27
  207. llama_stack_api/file_processors/api.py +0 -64
  208. llama_stack_api/file_processors/fastapi_routes.py +0 -78
  209. llama_stack_api/file_processors/models.py +0 -42
  210. llama_stack_api/files/__init__.py +0 -35
  211. llama_stack_api/files/api.py +0 -51
  212. llama_stack_api/files/fastapi_routes.py +0 -124
  213. llama_stack_api/files/models.py +0 -107
  214. llama_stack_api/inference.py +0 -1169
  215. llama_stack_api/inspect_api/__init__.py +0 -37
  216. llama_stack_api/inspect_api/api.py +0 -25
  217. llama_stack_api/inspect_api/fastapi_routes.py +0 -76
  218. llama_stack_api/inspect_api/models.py +0 -28
  219. llama_stack_api/internal/kvstore.py +0 -28
  220. llama_stack_api/internal/sqlstore.py +0 -81
  221. llama_stack_api/llama_stack_api/__init__.py +0 -945
  222. llama_stack_api/llama_stack_api/admin/__init__.py +0 -45
  223. llama_stack_api/llama_stack_api/admin/api.py +0 -72
  224. llama_stack_api/llama_stack_api/admin/fastapi_routes.py +0 -117
  225. llama_stack_api/llama_stack_api/admin/models.py +0 -113
  226. llama_stack_api/llama_stack_api/agents.py +0 -173
  227. llama_stack_api/llama_stack_api/batches/__init__.py +0 -40
  228. llama_stack_api/llama_stack_api/batches/api.py +0 -53
  229. llama_stack_api/llama_stack_api/batches/fastapi_routes.py +0 -113
  230. llama_stack_api/llama_stack_api/batches/models.py +0 -78
  231. llama_stack_api/llama_stack_api/benchmarks/__init__.py +0 -43
  232. llama_stack_api/llama_stack_api/benchmarks/api.py +0 -39
  233. llama_stack_api/llama_stack_api/benchmarks/fastapi_routes.py +0 -109
  234. llama_stack_api/llama_stack_api/benchmarks/models.py +0 -109
  235. llama_stack_api/llama_stack_api/common/__init__.py +0 -5
  236. llama_stack_api/llama_stack_api/common/content_types.py +0 -101
  237. llama_stack_api/llama_stack_api/common/errors.py +0 -95
  238. llama_stack_api/llama_stack_api/common/job_types.py +0 -38
  239. llama_stack_api/llama_stack_api/common/responses.py +0 -77
  240. llama_stack_api/llama_stack_api/common/training_types.py +0 -47
  241. llama_stack_api/llama_stack_api/common/type_system.py +0 -146
  242. llama_stack_api/llama_stack_api/connectors.py +0 -146
  243. llama_stack_api/llama_stack_api/conversations.py +0 -270
  244. llama_stack_api/llama_stack_api/datasetio.py +0 -55
  245. llama_stack_api/llama_stack_api/datasets/__init__.py +0 -61
  246. llama_stack_api/llama_stack_api/datasets/api.py +0 -35
  247. llama_stack_api/llama_stack_api/datasets/fastapi_routes.py +0 -104
  248. llama_stack_api/llama_stack_api/datasets/models.py +0 -152
  249. llama_stack_api/llama_stack_api/datatypes.py +0 -373
  250. llama_stack_api/llama_stack_api/eval.py +0 -137
  251. llama_stack_api/llama_stack_api/file_processors/__init__.py +0 -27
  252. llama_stack_api/llama_stack_api/file_processors/api.py +0 -64
  253. llama_stack_api/llama_stack_api/file_processors/fastapi_routes.py +0 -78
  254. llama_stack_api/llama_stack_api/file_processors/models.py +0 -42
  255. llama_stack_api/llama_stack_api/files/__init__.py +0 -35
  256. llama_stack_api/llama_stack_api/files/api.py +0 -51
  257. llama_stack_api/llama_stack_api/files/fastapi_routes.py +0 -124
  258. llama_stack_api/llama_stack_api/files/models.py +0 -107
  259. llama_stack_api/llama_stack_api/inference.py +0 -1169
  260. llama_stack_api/llama_stack_api/inspect_api/__init__.py +0 -37
  261. llama_stack_api/llama_stack_api/inspect_api/api.py +0 -25
  262. llama_stack_api/llama_stack_api/inspect_api/fastapi_routes.py +0 -76
  263. llama_stack_api/llama_stack_api/inspect_api/models.py +0 -28
  264. llama_stack_api/llama_stack_api/internal/__init__.py +0 -9
  265. llama_stack_api/llama_stack_api/internal/kvstore.py +0 -28
  266. llama_stack_api/llama_stack_api/internal/sqlstore.py +0 -81
  267. llama_stack_api/llama_stack_api/models.py +0 -171
  268. llama_stack_api/llama_stack_api/openai_responses.py +0 -1468
  269. llama_stack_api/llama_stack_api/post_training.py +0 -370
  270. llama_stack_api/llama_stack_api/prompts.py +0 -203
  271. llama_stack_api/llama_stack_api/providers/__init__.py +0 -33
  272. llama_stack_api/llama_stack_api/providers/api.py +0 -16
  273. llama_stack_api/llama_stack_api/providers/fastapi_routes.py +0 -57
  274. llama_stack_api/llama_stack_api/providers/models.py +0 -24
  275. llama_stack_api/llama_stack_api/py.typed +0 -0
  276. llama_stack_api/llama_stack_api/rag_tool.py +0 -168
  277. llama_stack_api/llama_stack_api/resource.py +0 -37
  278. llama_stack_api/llama_stack_api/router_utils.py +0 -160
  279. llama_stack_api/llama_stack_api/safety.py +0 -132
  280. llama_stack_api/llama_stack_api/schema_utils.py +0 -208
  281. llama_stack_api/llama_stack_api/scoring.py +0 -93
  282. llama_stack_api/llama_stack_api/scoring_functions.py +0 -211
  283. llama_stack_api/llama_stack_api/shields.py +0 -93
  284. llama_stack_api/llama_stack_api/tools.py +0 -226
  285. llama_stack_api/llama_stack_api/vector_io.py +0 -941
  286. llama_stack_api/llama_stack_api/vector_stores.py +0 -53
  287. llama_stack_api/llama_stack_api/version.py +0 -9
  288. llama_stack_api/models.py +0 -171
  289. llama_stack_api/openai_responses.py +0 -1468
  290. llama_stack_api/post_training.py +0 -370
  291. llama_stack_api/prompts.py +0 -203
  292. llama_stack_api/providers/__init__.py +0 -33
  293. llama_stack_api/providers/api.py +0 -16
  294. llama_stack_api/providers/fastapi_routes.py +0 -57
  295. llama_stack_api/providers/models.py +0 -24
  296. llama_stack_api/py.typed +0 -0
  297. llama_stack_api/rag_tool.py +0 -168
  298. llama_stack_api/resource.py +0 -37
  299. llama_stack_api/router_utils.py +0 -160
  300. llama_stack_api/safety.py +0 -132
  301. llama_stack_api/schema_utils.py +0 -208
  302. llama_stack_api/scoring.py +0 -93
  303. llama_stack_api/scoring_functions.py +0 -211
  304. llama_stack_api/shields.py +0 -93
  305. llama_stack_api/tools.py +0 -226
  306. llama_stack_api/vector_io.py +0 -941
  307. llama_stack_api/vector_stores.py +0 -53
  308. llama_stack_api/version.py +0 -9
  309. {llama_stack-0.4.3.dist-info → llama_stack-0.5.0.dist-info}/WHEEL +0 -0
  310. {llama_stack-0.4.3.dist-info → llama_stack-0.5.0.dist-info}/entry_points.txt +0 -0
  311. {llama_stack-0.4.3.dist-info → llama_stack-0.5.0.dist-info}/licenses/LICENSE +0 -0
@@ -1,37 +0,0 @@
1
- # Copyright (c) Meta Platforms, Inc. and affiliates.
2
- # All rights reserved.
3
- #
4
- # This source code is licensed under the terms described in the LICENSE file in
5
- # the root directory of this source tree.
6
-
7
- """Inspect API protocol and models.
8
-
9
- This module contains the Inspect protocol definition.
10
- Pydantic models are defined in llama_stack_api.inspect.models.
11
- The FastAPI router is defined in llama_stack_api.inspect.fastapi_routes.
12
- """
13
-
14
- # Import fastapi_routes for router factory access
15
- from . import fastapi_routes
16
-
17
- # Import protocol for re-export
18
- from .api import Inspect
19
-
20
- # Import models for re-export
21
- from .models import (
22
- ApiFilter,
23
- HealthInfo,
24
- ListRoutesResponse,
25
- RouteInfo,
26
- VersionInfo,
27
- )
28
-
29
- __all__ = [
30
- "Inspect",
31
- "ApiFilter",
32
- "HealthInfo",
33
- "ListRoutesResponse",
34
- "RouteInfo",
35
- "VersionInfo",
36
- "fastapi_routes",
37
- ]
@@ -1,25 +0,0 @@
1
- # Copyright (c) Meta Platforms, Inc. and affiliates.
2
- # All rights reserved.
3
- #
4
- # This source code is licensed under the terms described in the LICENSE file in
5
- # the root directory of this source tree.
6
-
7
- from typing import Protocol, runtime_checkable
8
-
9
- from .models import (
10
- ApiFilter,
11
- HealthInfo,
12
- ListRoutesResponse,
13
- VersionInfo,
14
- )
15
-
16
-
17
- @runtime_checkable
18
- class Inspect(Protocol):
19
- """APIs for inspecting the Llama Stack service, including health status, available API routes with methods and implementing providers."""
20
-
21
- async def list_routes(self, api_filter: ApiFilter | None = None) -> ListRoutesResponse: ...
22
-
23
- async def health(self) -> HealthInfo: ...
24
-
25
- async def version(self) -> VersionInfo: ...
@@ -1,76 +0,0 @@
1
- # Copyright (c) Meta Platforms, Inc. and affiliates.
2
- # All rights reserved.
3
- #
4
- # This source code is licensed under the terms described in the LICENSE file in
5
- # the root directory of this source tree.
6
-
7
- """FastAPI router for the Inspect API.
8
-
9
- This module defines the FastAPI router for the Inspect API using standard
10
- FastAPI route decorators.
11
- """
12
-
13
- from typing import Annotated
14
-
15
- from fastapi import APIRouter, Query
16
-
17
- from llama_stack_api.router_utils import PUBLIC_ROUTE_KEY, standard_responses
18
- from llama_stack_api.version import LLAMA_STACK_API_V1
19
-
20
- from .api import Inspect
21
- from .models import (
22
- ApiFilter,
23
- HealthInfo,
24
- ListRoutesResponse,
25
- VersionInfo,
26
- )
27
-
28
-
29
- def create_router(impl: Inspect) -> APIRouter:
30
- """Create a FastAPI router for the Inspect API."""
31
- router = APIRouter(
32
- prefix=f"/{LLAMA_STACK_API_V1}",
33
- tags=["Inspect"],
34
- responses=standard_responses,
35
- )
36
-
37
- @router.get(
38
- "/inspect/routes",
39
- response_model=ListRoutesResponse,
40
- summary="List routes.",
41
- description="List all available API routes with their methods and implementing providers.",
42
- responses={200: {"description": "Response containing information about all available routes."}},
43
- )
44
- async def list_routes(
45
- api_filter: Annotated[
46
- ApiFilter | None,
47
- Query(
48
- description="Optional filter to control which routes are returned. Can be an API level ('v1', 'v1alpha', 'v1beta') to show non-deprecated routes at that level, or 'deprecated' to show deprecated routes across all levels. If not specified, returns all non-deprecated routes."
49
- ),
50
- ] = None,
51
- ) -> ListRoutesResponse:
52
- return await impl.list_routes(api_filter)
53
-
54
- @router.get(
55
- "/health",
56
- response_model=HealthInfo,
57
- summary="Get health status.",
58
- description="Get the current health status of the service.",
59
- responses={200: {"description": "Health information indicating if the service is operational."}},
60
- openapi_extra={PUBLIC_ROUTE_KEY: True},
61
- )
62
- async def health() -> HealthInfo:
63
- return await impl.health()
64
-
65
- @router.get(
66
- "/version",
67
- response_model=VersionInfo,
68
- summary="Get version.",
69
- description="Get the version of the service.",
70
- responses={200: {"description": "Version information containing the service version number."}},
71
- openapi_extra={PUBLIC_ROUTE_KEY: True},
72
- )
73
- async def version() -> VersionInfo:
74
- return await impl.version()
75
-
76
- return router
@@ -1,28 +0,0 @@
1
- # Copyright (c) Meta Platforms, Inc. and affiliates.
2
- # All rights reserved.
3
- #
4
- # This source code is licensed under the terms described in the LICENSE file in
5
- # the root directory of this source tree.
6
-
7
- """Pydantic models for Inspect API requests and responses.
8
-
9
- This module re-exports models from llama_stack_api.admin.models to ensure
10
- a single source of truth and avoid type conflicts.
11
- """
12
-
13
- # Import and re-export shared models from admin
14
- from llama_stack_api.admin.models import (
15
- ApiFilter,
16
- HealthInfo,
17
- ListRoutesResponse,
18
- RouteInfo,
19
- VersionInfo,
20
- )
21
-
22
- __all__ = [
23
- "ApiFilter",
24
- "RouteInfo",
25
- "HealthInfo",
26
- "VersionInfo",
27
- "ListRoutesResponse",
28
- ]
@@ -1,28 +0,0 @@
1
- # Copyright (c) Meta Platforms, Inc. and affiliates.
2
- # All rights reserved.
3
- #
4
- # This source code is licensed under the terms described in the LICENSE file in
5
- # the root directory of this source tree.
6
-
7
- from datetime import datetime
8
- from typing import Protocol
9
-
10
-
11
- class KVStore(Protocol):
12
- """Protocol for simple key/value storage backends."""
13
-
14
- # TODO: make the value type bytes instead of str
15
- async def set(self, key: str, value: str, expiration: datetime | None = None) -> None: ...
16
-
17
- async def get(self, key: str) -> str | None: ...
18
-
19
- async def delete(self, key: str) -> None: ...
20
-
21
- async def values_in_range(self, start_key: str, end_key: str) -> list[str]: ...
22
-
23
- async def keys_in_range(self, start_key: str, end_key: str) -> list[str]: ...
24
-
25
- async def shutdown(self) -> None: ...
26
-
27
-
28
- __all__ = ["KVStore"]
@@ -1,81 +0,0 @@
1
- # Copyright (c) Meta Platforms, Inc. and affiliates.
2
- # All rights reserved.
3
- #
4
- # This source code is licensed under the terms described in the LICENSE file in
5
- # the root directory of this source tree.
6
-
7
- from collections.abc import Mapping, Sequence
8
- from enum import Enum
9
- from typing import Any, Literal, Protocol
10
-
11
- from pydantic import BaseModel
12
-
13
- from llama_stack_api import PaginatedResponse
14
-
15
-
16
- class ColumnType(Enum):
17
- INTEGER = "INTEGER"
18
- STRING = "STRING"
19
- TEXT = "TEXT"
20
- FLOAT = "FLOAT"
21
- BOOLEAN = "BOOLEAN"
22
- JSON = "JSON"
23
- DATETIME = "DATETIME"
24
-
25
-
26
- class ColumnDefinition(BaseModel):
27
- type: ColumnType
28
- primary_key: bool = False
29
- nullable: bool = True
30
- default: Any = None
31
-
32
-
33
- class SqlStore(Protocol):
34
- """Protocol for common SQL-store functionality."""
35
-
36
- async def create_table(self, table: str, schema: Mapping[str, ColumnType | ColumnDefinition]) -> None: ...
37
-
38
- async def insert(self, table: str, data: Mapping[str, Any] | Sequence[Mapping[str, Any]]) -> None: ...
39
-
40
- async def upsert(
41
- self,
42
- table: str,
43
- data: Mapping[str, Any],
44
- conflict_columns: list[str],
45
- update_columns: list[str] | None = None,
46
- ) -> None: ...
47
-
48
- async def fetch_all(
49
- self,
50
- table: str,
51
- where: Mapping[str, Any] | None = None,
52
- where_sql: str | None = None,
53
- limit: int | None = None,
54
- order_by: list[tuple[str, Literal["asc", "desc"]]] | None = None,
55
- cursor: tuple[str, str] | None = None,
56
- ) -> PaginatedResponse: ...
57
-
58
- async def fetch_one(
59
- self,
60
- table: str,
61
- where: Mapping[str, Any] | None = None,
62
- where_sql: str | None = None,
63
- order_by: list[tuple[str, Literal["asc", "desc"]]] | None = None,
64
- ) -> dict[str, Any] | None: ...
65
-
66
- async def update(self, table: str, data: Mapping[str, Any], where: Mapping[str, Any]) -> None: ...
67
-
68
- async def delete(self, table: str, where: Mapping[str, Any]) -> None: ...
69
-
70
- async def add_column_if_not_exists(
71
- self,
72
- table: str,
73
- column_name: str,
74
- column_type: ColumnType,
75
- nullable: bool = True,
76
- ) -> None: ...
77
-
78
- async def shutdown(self) -> None: ...
79
-
80
-
81
- __all__ = ["ColumnDefinition", "ColumnType", "SqlStore"]