tiennm99/cheahjs-free-llm-api-resources
1
0 Fork 0
mirror of https://github.com/tiennm99/cheahjs-free-llm-api-resources.git synced 2026-10-15 22:14:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

gemini: fetch embedding limits

Browse Source
This commit is contained in:
Jun Siang Cheah committed 2024-08-31 11:57:06 +01:00
1 parent 4f6cc828b6
commit 71b943cf81
2 files changed
+11 -7
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+3 -4
View File
@@ -42,7 +42,7 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Zephyr 7B Beta</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr>
<td rowspan="8"><a href="https://aistudio.google.com" target="_blank">Google AI Studio</a></td>
<td rowspan="6">Data is used for training (when used outside of the UK/CH/EEA/EU).</td>
<td rowspan="8">Data is used for training (when used outside of the UK/CH/EEA/EU).</td>
<td>Gemini 1.5 Flash</td>
<td>1000000 tokens/minute<br>1500 requests/day<br>15 requests/minute</td>
</tr>
@@ -69,11 +69,10 @@ This lists various services that provide free access or credits towards API-base
<tr>
<td rowspan="2"></td>
<td>text-embedding-004</td>
<td>1500 requests/min<br>100 content/batch</td>
<td rowspan="2">150 batch requests/minute<br>1500 requests/minute<br>100 content/batch</td>
</tr>
<tr>
<td>embedding-001</td>
<td>1500 requests/min<br>100 content/batch</td>
</tr><tr>
<td rowspan="3"><a href="https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden" target="_blank">Google Cloud Vertex AI</a></td>
<td rowspan="3">Very stringent payment verification for Google Cloud.</td>
@@ -93,7 +92,7 @@ This lists various services that provide free access or credits towards API-base
<td></td>
</tr><tr>
<td rowspan="2"><a href="https://cohere.com" target="_blank">Cohere</a></td>
<td rowspan="2">10 requests/min<br>1000 requests/month</td>
<td rowspan="2"><a href="https://docs.cohere.com/docs/rate-limits">20 requests/min<br>1000 requests/month</a></td>
<td>Command-R</td>
<td>Shared Limit</td>
</tr>
src/pull_available_models.py
+8 -3
View File
@@ -423,6 +423,12 @@ def fetch_gemini_limits():
elif quota.metric == 'generativelanguage.googleapis.com/generate_content_free_tier_requests':
for dimension in quota.dimensions_infos:
models[dimension.dimensions.get("model")][f"requests/{quota.refresh_interval}"] = dimension.details.value
elif quota.metric == "generativelanguage.googleapis.com/embed_text_requests":
for dimension in quota.dimensions_infos:
models["project-embedding"][f"requests/{quota.refresh_interval}"] = dimension.details.value
elif quota.metric == "generativelanguage.googleapis.com/batch_embed_text_requests":
for dimension in quota.dimensions_infos:
models["project-embedding"][f"batch requests/{quota.refresh_interval}"] = dimension.details.value
pprint(models)
return models
@@ -463,7 +469,7 @@ def main():
table += f"""<tr>
<td rowspan="8"><a href="https://aistudio.google.com" target="_blank">Google AI Studio</a></td>
<td rowspan="6">Data is used for training (when used outside of the UK/CH/EEA/EU).</td>
<td rowspan="8">Data is used for training (when used outside of the UK/CH/EEA/EU).</td>
<td>Gemini 1.5 Flash</td>
<td>{get_human_limits({"limits": gemini_models["gemini-1.5-flash"]})}</td>
</tr>
@@ -490,11 +496,10 @@ def main():
<tr>
<td rowspan="2"></td>
<td>text-embedding-004</td>
<td>1500 requests/min<br>100 content/batch</td>
<td rowspan="2">{get_human_limits({"limits": gemini_models["project-embedding"]})}<br>100 content/batch</td>
</tr>
<tr>
<td>embedding-001</td>
<td>1500 requests/min<br>100 content/batch</td>
</tr>"""
table += """<tr>