ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
This commit is contained in:
@@ -0,0 +1,548 @@
|
||||
{
|
||||
"schema_version": "chapter3-evidence-v1",
|
||||
"experiment": "3-4",
|
||||
"run_id": "20260729T182754Z-3_4-d21199a0",
|
||||
"provenance": {
|
||||
"captured_at": "2026-07-29T18:27:54.233593+00:00",
|
||||
"git_revision": "4a7f37cf278bd15948c409f14533017c4c7fbc29",
|
||||
"python": "3.11.4 (main, Jul 5 2023, 08:40:20) [Clang 14.0.6 ]",
|
||||
"platform": "macOS-26.3-arm64-arm-64bit",
|
||||
"credential_presence": {
|
||||
"ARK_API_KEY": true,
|
||||
"MOONSHOT_API_KEY": true,
|
||||
"OPENAI_API_KEY": true,
|
||||
"GEMINI_API_KEY": true,
|
||||
"SILICONFLOW_API_KEY": true
|
||||
}
|
||||
},
|
||||
"status": "partial",
|
||||
"configuration": {
|
||||
"embedding_model": "Qwen/Qwen3-Embedding-0.6B",
|
||||
"model_revision": "97b0c614be4d77ee51c0cef4e5f07c00f9eb65b3",
|
||||
"device": "cpu",
|
||||
"seed": 37,
|
||||
"dimension": 1024,
|
||||
"documents": 40,
|
||||
"queries": 20,
|
||||
"top_k": 3,
|
||||
"annoy_runtime": {
|
||||
"kind": "docker-linux-aarch64",
|
||||
"reason": "host macOS ARM ANNOY extension failed health check (returned fewer than k items)",
|
||||
"base_image": "python:3.11-slim",
|
||||
"base_image_repo_digests": [
|
||||
"python@sha256:db3ff2e1800a8581e2c48a27c3995339d47bdf046da21c7627accd3d51053a93"
|
||||
],
|
||||
"container_setup_and_run_wall_ms": 38303.133
|
||||
}
|
||||
},
|
||||
"acceptance": {
|
||||
"real_embedding_model": true,
|
||||
"same_vectors_and_queries": true,
|
||||
"exact_search_ground_truth": true,
|
||||
"recall_latency_build_size_measured": true,
|
||||
"incremental_behavior_measured": true,
|
||||
"both_backends_recall_at_least_0_8": true,
|
||||
"passed": false
|
||||
},
|
||||
"summary": {
|
||||
"embedding_latency_ms": 8671.983,
|
||||
"annoy": {
|
||||
"build_ms": 5.385,
|
||||
"recall_at_k": 1.0,
|
||||
"query_latency_ms": {
|
||||
"mean": 0.10229384060949087,
|
||||
"p50": 0.09818747639656067,
|
||||
"p95": 0.12266857083886863
|
||||
},
|
||||
"serialized_bytes": 542256,
|
||||
"incremental_update": {
|
||||
"items_added": 8,
|
||||
"latency_ms": 2.763,
|
||||
"requires_full_rebuild": true,
|
||||
"recall_at_k_after_update": 1.0
|
||||
}
|
||||
},
|
||||
"hnsw": {
|
||||
"build_ms": 1.375,
|
||||
"recall_at_k": 1.0,
|
||||
"query_latency_ms": {
|
||||
"mean": 0.03809796180576086,
|
||||
"p50": 0.03702123649418354,
|
||||
"p95": 0.042385491542518146
|
||||
},
|
||||
"serialized_bytes": 135912,
|
||||
"incremental_update": {
|
||||
"items_added": 8,
|
||||
"latency_ms": 0.919,
|
||||
"requires_full_rebuild": false,
|
||||
"recall_at_k_after_update": 1.0
|
||||
}
|
||||
}
|
||||
},
|
||||
"corpus": {
|
||||
"doc_ids": [
|
||||
"doc_0000",
|
||||
"doc_0001",
|
||||
"doc_0002",
|
||||
"doc_0003",
|
||||
"doc_0004",
|
||||
"doc_0005",
|
||||
"doc_0006",
|
||||
"doc_0007",
|
||||
"doc_0008",
|
||||
"doc_0009",
|
||||
"doc_0010",
|
||||
"doc_0011",
|
||||
"doc_0012",
|
||||
"doc_0013",
|
||||
"doc_0014",
|
||||
"doc_0015",
|
||||
"doc_0016",
|
||||
"doc_0017",
|
||||
"doc_0018",
|
||||
"doc_0019",
|
||||
"doc_0020",
|
||||
"doc_0021",
|
||||
"doc_0022",
|
||||
"doc_0023",
|
||||
"doc_0024",
|
||||
"doc_0025",
|
||||
"doc_0026",
|
||||
"doc_0027",
|
||||
"doc_0028",
|
||||
"doc_0029",
|
||||
"doc_0030",
|
||||
"doc_0031",
|
||||
"doc_0032",
|
||||
"doc_0033",
|
||||
"doc_0034",
|
||||
"doc_0035",
|
||||
"doc_0036",
|
||||
"doc_0037",
|
||||
"doc_0038",
|
||||
"doc_0039"
|
||||
],
|
||||
"texts": [
|
||||
"Topic: vector search. Approximate nearest-neighbor indexes accelerate semantic vector retrieval. A concise technical overview. Document revision 0000.",
|
||||
"Topic: database transactions. Database transactions use atomicity, consistency, isolation and durability. A concise technical overview. Document revision 0001.",
|
||||
"Topic: photosynthesis. Green plants turn sunlight and carbon dioxide into chemical energy. A concise technical overview. Document revision 0002.",
|
||||
"Topic: quantum entanglement. Entangled particles exhibit correlated quantum measurement outcomes. A concise technical overview. Document revision 0003.",
|
||||
"Topic: contract law. A valid contract generally requires offer acceptance and consideration. A concise technical overview. Document revision 0004.",
|
||||
"Topic: neural networks. Deep neural networks learn layered nonlinear representations from data. A concise technical overview. Document revision 0005.",
|
||||
"Topic: cybersecurity. Zero trust security continuously verifies identity and device posture. A concise technical overview. Document revision 0006.",
|
||||
"Topic: volcanoes. Volcanoes form when magma rises through fractures in the planetary crust. A concise technical overview. Document revision 0007.",
|
||||
"Topic: water cycle. Evaporation condensation precipitation and runoff form the water cycle. A concise technical overview. Document revision 0008.",
|
||||
"Topic: operating systems. An operating system schedules processes and manages memory and devices. A concise technical overview. Document revision 0009.",
|
||||
"Topic: HTTP errors. HTTP status 403 means a server understood but refused a request. A concise technical overview. Document revision 0010.",
|
||||
"Topic: machine translation. Multilingual models translate meaning between natural languages. A concise technical overview. Document revision 0011.",
|
||||
"Topic: financial risk. Portfolio diversification reduces exposure to idiosyncratic financial risk. A concise technical overview. Document revision 0012.",
|
||||
"Topic: medical imaging. Radiology systems analyze X-rays CT scans and magnetic resonance images. A concise technical overview. Document revision 0013.",
|
||||
"Topic: supply chains. Supply chain planning coordinates inventory logistics demand and suppliers. A concise technical overview. Document revision 0014.",
|
||||
"Topic: climate science. Climate models simulate long-term interactions among atmosphere ocean and land. A concise technical overview. Document revision 0015.",
|
||||
"Topic: CPU instructions. SIMD instructions apply one operation to several packed numeric values. A concise technical overview. Document revision 0016.",
|
||||
"Topic: compiler design. A compiler parses source code optimizes intermediate form and emits machine code. A concise technical overview. Document revision 0017.",
|
||||
"Topic: graph theory. Graph algorithms traverse vertices and edges to discover paths and communities. A concise technical overview. Document revision 0018.",
|
||||
"Topic: astronomy. Astronomers infer stellar properties from spectra luminosity and orbital motion. A concise technical overview. Document revision 0019.",
|
||||
"Topic: vector search. Approximate nearest-neighbor indexes accelerate semantic vector retrieval. This passage explains the central mechanism and its practical use. Document revision 0020.",
|
||||
"Topic: database transactions. Database transactions use atomicity, consistency, isolation and durability. This passage explains the central mechanism and its practical use. Document revision 0021.",
|
||||
"Topic: photosynthesis. Green plants turn sunlight and carbon dioxide into chemical energy. This passage explains the central mechanism and its practical use. Document revision 0022.",
|
||||
"Topic: quantum entanglement. Entangled particles exhibit correlated quantum measurement outcomes. This passage explains the central mechanism and its practical use. Document revision 0023.",
|
||||
"Topic: contract law. A valid contract generally requires offer acceptance and consideration. This passage explains the central mechanism and its practical use. Document revision 0024.",
|
||||
"Topic: neural networks. Deep neural networks learn layered nonlinear representations from data. This passage explains the central mechanism and its practical use. Document revision 0025.",
|
||||
"Topic: cybersecurity. Zero trust security continuously verifies identity and device posture. This passage explains the central mechanism and its practical use. Document revision 0026.",
|
||||
"Topic: volcanoes. Volcanoes form when magma rises through fractures in the planetary crust. This passage explains the central mechanism and its practical use. Document revision 0027.",
|
||||
"Topic: water cycle. Evaporation condensation precipitation and runoff form the water cycle. This passage explains the central mechanism and its practical use. Document revision 0028.",
|
||||
"Topic: operating systems. An operating system schedules processes and manages memory and devices. This passage explains the central mechanism and its practical use. Document revision 0029.",
|
||||
"Topic: HTTP errors. HTTP status 403 means a server understood but refused a request. This passage explains the central mechanism and its practical use. Document revision 0030.",
|
||||
"Topic: machine translation. Multilingual models translate meaning between natural languages. This passage explains the central mechanism and its practical use. Document revision 0031.",
|
||||
"Topic: financial risk. Portfolio diversification reduces exposure to idiosyncratic financial risk. This passage explains the central mechanism and its practical use. Document revision 0032.",
|
||||
"Topic: medical imaging. Radiology systems analyze X-rays CT scans and magnetic resonance images. This passage explains the central mechanism and its practical use. Document revision 0033.",
|
||||
"Topic: supply chains. Supply chain planning coordinates inventory logistics demand and suppliers. This passage explains the central mechanism and its practical use. Document revision 0034.",
|
||||
"Topic: climate science. Climate models simulate long-term interactions among atmosphere ocean and land. This passage explains the central mechanism and its practical use. Document revision 0035.",
|
||||
"Topic: CPU instructions. SIMD instructions apply one operation to several packed numeric values. This passage explains the central mechanism and its practical use. Document revision 0036.",
|
||||
"Topic: compiler design. A compiler parses source code optimizes intermediate form and emits machine code. This passage explains the central mechanism and its practical use. Document revision 0037.",
|
||||
"Topic: graph theory. Graph algorithms traverse vertices and edges to discover paths and communities. This passage explains the central mechanism and its practical use. Document revision 0038.",
|
||||
"Topic: astronomy. Astronomers infer stellar properties from spectra luminosity and orbital motion. This passage explains the central mechanism and its practical use. Document revision 0039."
|
||||
],
|
||||
"queries": [
|
||||
"Find technical information about vector search.",
|
||||
"Find technical information about database transactions.",
|
||||
"Find technical information about photosynthesis.",
|
||||
"Find technical information about quantum entanglement.",
|
||||
"Find technical information about contract law.",
|
||||
"Find technical information about neural networks.",
|
||||
"Find technical information about cybersecurity.",
|
||||
"Find technical information about volcanoes.",
|
||||
"Find technical information about water cycle.",
|
||||
"Find technical information about operating systems.",
|
||||
"Find technical information about HTTP errors.",
|
||||
"Find technical information about machine translation.",
|
||||
"Find technical information about financial risk.",
|
||||
"Find technical information about medical imaging.",
|
||||
"Find technical information about supply chains.",
|
||||
"Find technical information about climate science.",
|
||||
"Find technical information about CPU instructions.",
|
||||
"Find technical information about compiler design.",
|
||||
"Find technical information about graph theory.",
|
||||
"Find technical information about astronomy."
|
||||
]
|
||||
},
|
||||
"results": {
|
||||
"annoy": {
|
||||
"build_ms": 5.385,
|
||||
"recall_at_k": 1.0,
|
||||
"query_latency_ms": {
|
||||
"mean": 0.10229384060949087,
|
||||
"p50": 0.09818747639656067,
|
||||
"p95": 0.12266857083886863
|
||||
},
|
||||
"serialized_bytes": 542256,
|
||||
"rankings": [
|
||||
{
|
||||
"query_index": 0,
|
||||
"doc_ids": [
|
||||
"doc_0000",
|
||||
"doc_0020",
|
||||
"doc_0018"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 1,
|
||||
"doc_ids": [
|
||||
"doc_0001",
|
||||
"doc_0021",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 2,
|
||||
"doc_ids": [
|
||||
"doc_0002",
|
||||
"doc_0022",
|
||||
"doc_0008"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 3,
|
||||
"doc_ids": [
|
||||
"doc_0003",
|
||||
"doc_0023",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 4,
|
||||
"doc_ids": [
|
||||
"doc_0024",
|
||||
"doc_0004",
|
||||
"doc_0003"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 5,
|
||||
"doc_ids": [
|
||||
"doc_0005",
|
||||
"doc_0025",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 6,
|
||||
"doc_ids": [
|
||||
"doc_0006",
|
||||
"doc_0026",
|
||||
"doc_0018"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 7,
|
||||
"doc_ids": [
|
||||
"doc_0007",
|
||||
"doc_0027",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 8,
|
||||
"doc_ids": [
|
||||
"doc_0008",
|
||||
"doc_0028",
|
||||
"doc_0015"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 9,
|
||||
"doc_ids": [
|
||||
"doc_0009",
|
||||
"doc_0029",
|
||||
"doc_0016"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 10,
|
||||
"doc_ids": [
|
||||
"doc_0010",
|
||||
"doc_0030",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 11,
|
||||
"doc_ids": [
|
||||
"doc_0011",
|
||||
"doc_0031",
|
||||
"doc_0025"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 12,
|
||||
"doc_ids": [
|
||||
"doc_0012",
|
||||
"doc_0018",
|
||||
"doc_0005"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 13,
|
||||
"doc_ids": [
|
||||
"doc_0013",
|
||||
"doc_0000",
|
||||
"doc_0005"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 14,
|
||||
"doc_ids": [
|
||||
"doc_0014",
|
||||
"doc_0008",
|
||||
"doc_0028"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 15,
|
||||
"doc_ids": [
|
||||
"doc_0015",
|
||||
"doc_0008",
|
||||
"doc_0028"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 16,
|
||||
"doc_ids": [
|
||||
"doc_0016",
|
||||
"doc_0029",
|
||||
"doc_0017"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 17,
|
||||
"doc_ids": [
|
||||
"doc_0017",
|
||||
"doc_0016",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 18,
|
||||
"doc_ids": [
|
||||
"doc_0018",
|
||||
"doc_0005",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 19,
|
||||
"doc_ids": [
|
||||
"doc_0019",
|
||||
"doc_0000",
|
||||
"doc_0013"
|
||||
]
|
||||
}
|
||||
],
|
||||
"incremental_update": {
|
||||
"items_added": 8,
|
||||
"latency_ms": 2.763,
|
||||
"requires_full_rebuild": true,
|
||||
"recall_at_k_after_update": 1.0
|
||||
}
|
||||
},
|
||||
"hnsw": {
|
||||
"build_ms": 1.375,
|
||||
"recall_at_k": 1.0,
|
||||
"query_latency_ms": {
|
||||
"mean": 0.03809796180576086,
|
||||
"p50": 0.03702123649418354,
|
||||
"p95": 0.042385491542518146
|
||||
},
|
||||
"serialized_bytes": 135912,
|
||||
"rankings": [
|
||||
{
|
||||
"query_index": 0,
|
||||
"doc_ids": [
|
||||
"doc_0000",
|
||||
"doc_0020",
|
||||
"doc_0018"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 1,
|
||||
"doc_ids": [
|
||||
"doc_0001",
|
||||
"doc_0021",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 2,
|
||||
"doc_ids": [
|
||||
"doc_0002",
|
||||
"doc_0022",
|
||||
"doc_0008"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 3,
|
||||
"doc_ids": [
|
||||
"doc_0003",
|
||||
"doc_0023",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 4,
|
||||
"doc_ids": [
|
||||
"doc_0024",
|
||||
"doc_0004",
|
||||
"doc_0003"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 5,
|
||||
"doc_ids": [
|
||||
"doc_0005",
|
||||
"doc_0025",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 6,
|
||||
"doc_ids": [
|
||||
"doc_0006",
|
||||
"doc_0026",
|
||||
"doc_0018"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 7,
|
||||
"doc_ids": [
|
||||
"doc_0007",
|
||||
"doc_0027",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 8,
|
||||
"doc_ids": [
|
||||
"doc_0008",
|
||||
"doc_0028",
|
||||
"doc_0015"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 9,
|
||||
"doc_ids": [
|
||||
"doc_0009",
|
||||
"doc_0029",
|
||||
"doc_0016"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 10,
|
||||
"doc_ids": [
|
||||
"doc_0010",
|
||||
"doc_0030",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 11,
|
||||
"doc_ids": [
|
||||
"doc_0011",
|
||||
"doc_0031",
|
||||
"doc_0025"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 12,
|
||||
"doc_ids": [
|
||||
"doc_0012",
|
||||
"doc_0018",
|
||||
"doc_0005"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 13,
|
||||
"doc_ids": [
|
||||
"doc_0013",
|
||||
"doc_0000",
|
||||
"doc_0005"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 14,
|
||||
"doc_ids": [
|
||||
"doc_0014",
|
||||
"doc_0008",
|
||||
"doc_0028"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 15,
|
||||
"doc_ids": [
|
||||
"doc_0015",
|
||||
"doc_0008",
|
||||
"doc_0028"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 16,
|
||||
"doc_ids": [
|
||||
"doc_0016",
|
||||
"doc_0029",
|
||||
"doc_0017"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 17,
|
||||
"doc_ids": [
|
||||
"doc_0017",
|
||||
"doc_0016",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 18,
|
||||
"doc_ids": [
|
||||
"doc_0018",
|
||||
"doc_0005",
|
||||
"doc_0000"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query_index": 19,
|
||||
"doc_ids": [
|
||||
"doc_0019",
|
||||
"doc_0000",
|
||||
"doc_0013"
|
||||
]
|
||||
}
|
||||
],
|
||||
"incremental_update": {
|
||||
"items_added": 8,
|
||||
"latency_ms": 0.919,
|
||||
"requires_full_rebuild": false,
|
||||
"recall_at_k_after_update": 1.0
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,73 @@
|
||||
{
|
||||
"schema_version": "chapter3-evidence-v1",
|
||||
"experiment": "3-4",
|
||||
"run_id": "20260729T182754Z-3_4-d21199a0",
|
||||
"created_at": "2026-07-29T18:27:54.269138+00:00",
|
||||
"status": "partial",
|
||||
"run_dir": "/Users/boj/book/ai-agent-book/chapter3/dense-embedding/validation/runs/20260729T182754Z-3_4-d21199a0",
|
||||
"artifacts": {
|
||||
"evidence.json": "d04ecc4f2612d3559d402ff7c6d67e2e13cda27eb4f8e63f610e7a10b9052a7e",
|
||||
"receipts.json": "37517e5f3dc66819f61f5a7bb8ace1921282415f10551d2defa5c3eb0985b570"
|
||||
},
|
||||
"inputs": [
|
||||
{
|
||||
"path": "/Users/boj/book/ai-agent-book/chapter3/dense-embedding/indexing.py",
|
||||
"sha256": "80ca520a78f044b367edfe71ff4e4bb22fa80f00d4803831d17b2b8c14ba1f57",
|
||||
"bytes": 14977
|
||||
},
|
||||
{
|
||||
"path": "/Users/boj/book/ai-agent-book/chapter3/dense-embedding/benchmark.py",
|
||||
"sha256": "d5d72267ca683ec513acd422287ff6f7cd65c54c6eaad5d636b67b983dda7904",
|
||||
"bytes": 13883
|
||||
},
|
||||
{
|
||||
"path": "/Users/boj/book/ai-agent-book/chapter3/dense-embedding/docker_annoy_runner.py",
|
||||
"sha256": "f75ee2f5f81365143a6f8ad68c6706933f8012ca4792a643d8ae79bfc9621c70",
|
||||
"bytes": 2980
|
||||
}
|
||||
],
|
||||
"summary": {
|
||||
"embedding_latency_ms": 8671.983,
|
||||
"annoy": {
|
||||
"build_ms": 5.385,
|
||||
"recall_at_k": 1.0,
|
||||
"query_latency_ms": {
|
||||
"mean": 0.10229384060949087,
|
||||
"p50": 0.09818747639656067,
|
||||
"p95": 0.12266857083886863
|
||||
},
|
||||
"serialized_bytes": 542256,
|
||||
"incremental_update": {
|
||||
"items_added": 8,
|
||||
"latency_ms": 2.763,
|
||||
"requires_full_rebuild": true,
|
||||
"recall_at_k_after_update": 1.0
|
||||
}
|
||||
},
|
||||
"hnsw": {
|
||||
"build_ms": 1.375,
|
||||
"recall_at_k": 1.0,
|
||||
"query_latency_ms": {
|
||||
"mean": 0.03809796180576086,
|
||||
"p50": 0.03702123649418354,
|
||||
"p95": 0.042385491542518146
|
||||
},
|
||||
"serialized_bytes": 135912,
|
||||
"incremental_update": {
|
||||
"items_added": 8,
|
||||
"latency_ms": 0.919,
|
||||
"requires_full_rebuild": false,
|
||||
"recall_at_k_after_update": 1.0
|
||||
}
|
||||
}
|
||||
},
|
||||
"acceptance": {
|
||||
"real_embedding_model": true,
|
||||
"same_vectors_and_queries": true,
|
||||
"exact_search_ground_truth": true,
|
||||
"recall_latency_build_size_measured": true,
|
||||
"incremental_behavior_measured": true,
|
||||
"both_backends_recall_at_least_0_8": true,
|
||||
"passed": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user