mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-07 08:26:10 +00:00
Fix greptile review
This commit is contained in:
parent
8e943929a2
commit
b56fdf188e
2 changed files with 16 additions and 15 deletions
|
|
@ -124,7 +124,7 @@ MODEL_ID="gemini-2.0-flash-001"
|
|||
PROJECT_ID="YOUR_PROJECT_ID"
|
||||
|
||||
curl -X POST \
|
||||
"${LITELLM_PROXY_BASE_URL}/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:generateContent" \
|
||||
"${LITELLM_PROXY_BASE_URL}/vertex_ai/v1/projects/${PROJECT_ID}/locations/global/publishers/google/models/${MODEL_ID}:generateContent" \
|
||||
-H "Authorization: Bearer sk-your-litellm-key" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "x-pass-X-Vertex-AI-LLM-Request-Type: shared" \
|
||||
|
|
@ -143,7 +143,7 @@ A: The service account or Application Default Credentials (ADC) user does not ha
|
|||
**Q: What should I do if I get a `429 Quota exceeded` error?**
|
||||
A: This means you've hit the per-region QPM (queries per minute) or TPM (tokens per minute) quota. You can:
|
||||
- Request a quota increase from the [GCP Quotas console](https://console.cloud.google.com/iam-admin/quotas)
|
||||
- Add more regions to your LiteLLM configuration for load balancing (see the region balancing guide above)
|
||||
- Add more regions to your LiteLLM configuration for load balancing
|
||||
- Upgrade to [Provisioned Throughput](https://cloud.google.com/vertex-ai/generative-ai/docs/provisioned-throughput) for guaranteed capacity
|
||||
|
||||
**Q: How do I fix the `VERTEXAI_PROJECT not set` error?**
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
</defs>
|
||||
|
||||
<!-- Step 1: HTTP Request -->
|
||||
<g style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<g onclick="sendPrompt('What is the X-Vertex-AI-LLM-Shared-Request-Type header used for?')" style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<rect x="190" y="30" width="300" height="56" rx="8" stroke-width="0.5" style="fill:rgb(12, 68, 124);stroke:rgb(133, 183, 235);color:rgb(255, 255, 255);stroke-width:0.5px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto"/>
|
||||
<text x="340" y="52" text-anchor="middle" dominant-baseline="central" style="fill:rgb(181, 212, 244);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:14px;font-weight:500;text-anchor:middle;dominant-baseline:central">HTTP request</text>
|
||||
<text x="340" y="70" text-anchor="middle" dominant-baseline="central" style="fill:rgb(133, 183, 235);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:middle;dominant-baseline:central">X-Vertex-AI-LLM-Shared-Request-Type: priority</text>
|
||||
|
|
@ -17,7 +17,7 @@
|
|||
<text x="356" y="108" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:start;dominant-baseline:central">Vertex AI</text>
|
||||
|
||||
<!-- Step 2: Vertex response -->
|
||||
<g style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<g onclick="sendPrompt('What does Vertex AI return in usageMetadata.trafficType?')" style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<rect x="190" y="120" width="300" height="56" rx="8" stroke-width="0.5" style="fill:rgb(8, 80, 65);stroke:rgb(93, 202, 165);color:rgb(255, 255, 255);stroke-width:0.5px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto"/>
|
||||
<text x="340" y="142" text-anchor="middle" dominant-baseline="central" style="fill:rgb(159, 225, 203);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:14px;font-weight:500;text-anchor:middle;dominant-baseline:central">Vertex response</text>
|
||||
<text x="340" y="160" text-anchor="middle" dominant-baseline="central" style="fill:rgb(93, 202, 165);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:middle;dominant-baseline:central">usageMetadata.trafficType = ON_DEMAND_PRIORITY</text>
|
||||
|
|
@ -27,7 +27,7 @@
|
|||
<line x1="340" y1="176" x2="340" y2="210" marker-end="url(#arrow)" style="fill:none;stroke:rgb(156, 154, 146);color:rgb(255, 255, 255);stroke-width:1.5px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto"/>
|
||||
|
||||
<!-- Step 3: LiteLLM hidden params -->
|
||||
<g style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<g onclick="sendPrompt('Where does LiteLLM store the traffic_type field from Vertex?')" style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<rect x="190" y="210" width="300" height="56" rx="8" stroke-width="0.5" style="fill:rgb(60, 52, 137);stroke:rgb(175, 169, 236);color:rgb(255, 255, 255);stroke-width:0.5px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto"/>
|
||||
<text x="340" y="232" text-anchor="middle" dominant-baseline="central" style="fill:rgb(206, 203, 246);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:14px;font-weight:500;text-anchor:middle;dominant-baseline:central">LiteLLM stores it</text>
|
||||
<text x="340" y="250" text-anchor="middle" dominant-baseline="central" style="fill:rgb(175, 169, 236);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:middle;dominant-baseline:central">_hidden_params.provider_specific_fields.traffic_type</text>
|
||||
|
|
@ -37,26 +37,27 @@
|
|||
<line x1="340" y1="266" x2="340" y2="300" marker-end="url(#arrow)" style="fill:none;stroke:rgb(156, 154, 146);color:rgb(255, 255, 255);stroke-width:1.5px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto"/>
|
||||
|
||||
<!-- Step 4: completion_cost() -->
|
||||
<g style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<g onclick="sendPrompt('How does completion_cost() map traffic_type to service_tier?')" style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<rect x="190" y="300" width="300" height="56" rx="8" stroke-width="0.5" style="fill:rgb(99, 56, 6);stroke:rgb(239, 159, 39);color:rgb(255, 255, 255);stroke-width:0.5px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto"/>
|
||||
<text x="340" y="322" text-anchor="middle" dominant-baseline="central" style="fill:rgb(250, 199, 117);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:14px;font-weight:500;text-anchor:middle;dominant-baseline:central">completion_cost()</text>
|
||||
<text x="340" y="340" text-anchor="middle" dominant-baseline="central" style="fill:rgb(239, 159, 39);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:middle;dominant-baseline:central">Maps traffic_type ’ service_tier = "priority"</text>
|
||||
<text x="340" y="340" text-anchor="middle" dominant-baseline="central" style="fill:rgb(239, 159, 39);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:middle;dominant-baseline:central">Maps traffic_type → service_tier = "priority"</text>
|
||||
</g>
|
||||
|
||||
<!-- Arrow 4 -->
|
||||
<line x1="340" y1="356" x2="340" y2="390" marker-end="url(#arrow)" style="fill:none;stroke:rgb(156, 154, 146);color:rgb(255, 255, 255);stroke-width:1.5px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto"/>
|
||||
|
||||
<!-- Step 5: Pricing lookup -->
|
||||
<g style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<g onclick="sendPrompt('What pricing keys are used for priority tier in LiteLLM?')" style="fill:rgb(0, 0, 0);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto">
|
||||
<rect x="190" y="390" width="300" height="56" rx="8" stroke-width="0.5" style="fill:rgb(113, 43, 19);stroke:rgb(240, 153, 123);color:rgb(255, 255, 255);stroke-width:0.5px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:16px;font-weight:400;text-anchor:start;dominant-baseline:auto"/>
|
||||
<text x="340" y="412" text-anchor="middle" dominant-baseline="central" style="fill:rgb(245, 196, 179);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:14px;font-weight:500;text-anchor:middle;dominant-baseline:central">Pricing lookup</text>
|
||||
<text x="340" y="430" text-anchor="middle" dominant-baseline="central" style="fill:rgb(240, 153, 123);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:middle;dominant-baseline:central">input/output_cost_per_token_priority</text>
|
||||
</g>
|
||||
|
||||
<!-- Step numbers -->
|
||||
<text x="172" y="58" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">`</text>
|
||||
<text x="172" y="148" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">a</text>
|
||||
<text x="172" y="238" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">b</text>
|
||||
<text x="172" y="328" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">c</text>
|
||||
<text x="172" y="418" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">d</text>
|
||||
</svg>
|
||||
<!-- Step numbers in left margin -->
|
||||
<text x="172" y="58" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">①</text>
|
||||
<text x="172" y="148" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">②</text>
|
||||
<text x="172" y="238" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">③</text>
|
||||
<text x="172" y="328" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">④</text>
|
||||
<text x="172" y="418" text-anchor="end" dominant-baseline="central" style="fill:rgb(194, 192, 182);stroke:none;color:rgb(255, 255, 255);stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;opacity:1;font-family:"Anthropic Sans", -apple-system, "system-ui", "Segoe UI", sans-serif;font-size:12px;font-weight:400;text-anchor:end;dominant-baseline:central">⑤</text>
|
||||
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 12 KiB After Width: | Height: | Size: 13 KiB |
Loading…
Add table
Reference in a new issue