liqiang/ai-agent-book
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

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
Details
dependency resolution / resolve (3.11) (push) Canceled after 0s
Details
dependency resolution / resolve (3.13) (push) Canceled after 0s
Details
deploy-pages / build (push) Canceled after 0s
Details
deploy-pages / deploy (push) Canceled after 0s
Details
i18n consistency check / check (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
Details
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
Details
web-search-agent tests / test (push) Canceled after 0s
Details
web-search-agent tests / agentbook (push) Canceled after 0s
Details

Browse Source
This commit is contained in:
liqiang
2026-08-20 13:12:50 +00:00
commit b119135836
10275 changed files with 3284984 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
book-he/images/fig7-9.svg
+69
View File
@@ -0,0 +1,69 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 940 480" width="940" height="480" style="background:#ffffff">
<defs><marker id="ah" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#333333"/></marker><marker id="ah-compact" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto" markerUnits="userSpaceOnUse"><polygon points="0 0, 12 4, 0 8" fill="#333333"/></marker><marker id="ah-light" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#999999"/></marker></defs>
<rect x="20" y="65" width="220" height="250" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
<text x="130" y="88" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="19.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Multimodal observation</text>
<rect x="35" y="105" width="190" height="42" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="130" y="120" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Head camera</text>
<text x="130" y="138" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">224×224 RGB</text>
<rect x="35" y="160" width="190" height="42" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="130" y="175" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Left wrist camera</text>
<text x="130" y="193" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">224×224 RGB</text>
<rect x="35" y="215" width="190" height="42" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="130" y="230" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Right wrist camera</text>
<text x="130" y="248" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">224×224 RGB</text>
<rect x="35" y="275" width="190" height="30" rx="4" fill="#f5f5f5" stroke="#999999" stroke-width="2"/>
<text x="45" y="290" font-family="'Courier New', Courier, monospace" font-size="8.5" fill="#333333" text-anchor="start" dominant-baseline="central">14-dimensional joint state vector</text>
<rect x="280" y="65" width="310" height="250" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
<text x="435" y="88" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Vision-Language-Action model (VLA)</text>
<rect x="295" y="105" width="280" height="50" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
<text x="450" y="125" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Vision encoder</text>
<text x="450" y="145" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">SigLIP → visual tokens</text>
<line x1="435" y1="157" x2="435" y2="168" stroke="#333333" stroke-width="2" marker-end="url(#ah-compact)"/>
<rect x="295" y="170" width="280" height="50" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="450" y="190" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Language model</text>
<text x="450" y="210" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Llama 2 7B backbone</text>
<line x1="435" y1="222" x2="435" y2="233" stroke="#333333" stroke-width="2" marker-end="url(#ah-compact)"/>
<rect x="295" y="235" width="280" height="78" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
<text x="435" y="252" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Action decoder</text>
<text x="435" y="272" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">→ 14-dimensional continuous control vector</text>
<text x="435" y="298" font-family="'Courier New', Courier, monospace" font-size="8" fill="#333333" text-anchor="middle" dominant-baseline="central">Action chunking: generate 25 consecutive actions at once</text>
<line x1="240" y1="132" x2="278" y2="132" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
<line x1="240" y1="257" x2="278" y2="257" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
<rect x="300" y="345" width="260" height="32" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="430" y="361" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Instruction: "Put the can into the pot"</text>
<line x1="430" y1="345" x2="430" y2="315" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
<rect x="690" y="65" width="230" height="250" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
<text x="805" y="88" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">SAPIEN physics engine</text>
<rect x="705" y="105" width="200" height="55" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="805" y="125" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Dual-arm robot</text>
<text x="805" y="145" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">7 DOF each = 14-dimensional action</text>
<rect x="705" y="175" width="200" height="55" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
<text x="805" y="195" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="15" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Environment randomization</text>
<text x="805" y="215" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Position 60cm / orientation ±22.5°</text>
<rect x="705" y="245" width="200" height="55" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="805" y="265" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="10.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Collision detection + physics simulation</text>
<text x="805" y="285" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Rigid body / soft body / friction</text>
<line x1="590" y1="220" x2="688" y2="220" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
<text x="640" y="210.0" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle">Action</text>
<line x1="690" y1="130" x2="592" y2="130" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
<text x="640" y="120.0" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle">Observation</text>
<line x1="20" y1="385" x2="920" y2="385" stroke="#999999" stroke-width="2" stroke-dasharray="8,4"/>
<text x="440.0" y="408" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Evaluation metrics</text>
<rect x="60" y="425" width="180" height="75" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="150" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Success rate</text>
<text x="150" y="465" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Can inside pot</text>
<text x="150" y="483" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">and not fallen</text>
<rect x="260" y="425" width="180" height="75" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="350" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Completion time</text>
<text x="350" y="465" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">25 steps × 25 actions</text>
<text x="350" y="483" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">= 625 control steps</text>
<rect x="460" y="425" width="180" height="75" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="550" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Generalization ability</text>
<text x="550" y="465" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Cross-position/orientation</text>
<text x="550" y="483" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">/Appearance variant</text>
<rect x="660" y="425" width="180" height="75" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="750" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Sim-to-Real</text>
<text x="750" y="465" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Domain randomization</text>
<text x="750" y="483" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">→ Real migration</text>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 12 KiB