mirror of
https://github.com/tiennm99/litellm.git
synced 2026-08-07 00:24:03 +00:00
docs(prompt_management.md): update docs to show how to point to load balanced model name
This commit is contained in:
@@ -43,11 +43,15 @@ resp = litellm.completion(
|
||||
|
||||
```yaml
|
||||
model_list:
|
||||
- model_name: gpt-3.5-turbo
|
||||
- model_name: my-langfuse-model
|
||||
litellm_params:
|
||||
model: langfuse/gpt-3.5-turbo
|
||||
model: langfuse/openai-model
|
||||
prompt_id: "<langfuse_prompt_id>"
|
||||
api_key: os.environ/OPENAI_API_KEY
|
||||
- model_name: openai-model
|
||||
litellm_params:
|
||||
model: openai/gpt-3.5-turbo
|
||||
api_key: os.environ/OPENAI_API_KEY
|
||||
```
|
||||
|
||||
2. Start the proxy
|
||||
@@ -66,7 +70,7 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
|
||||
-H 'Content-Type: application/json' \
|
||||
-H 'Authorization: Bearer sk-1234' \
|
||||
-d '{
|
||||
"model": "gpt-3.5-turbo",
|
||||
"model": "my-langfuse-model",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
||||
@@ -7695,6 +7695,22 @@
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "embedding"
|
||||
},
|
||||
"voyage/voyage-finance-2": {
|
||||
"max_tokens": 32000,
|
||||
"max_input_tokens": 32000,
|
||||
"input_cost_per_token": 0.00000012,
|
||||
"output_cost_per_token": 0.000000,
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "embedding"
|
||||
},
|
||||
"voyage/voyage-lite-02-instruct": {
|
||||
"max_tokens": 4000,
|
||||
"max_input_tokens": 4000,
|
||||
"input_cost_per_token": 0.0000001,
|
||||
"output_cost_per_token": 0.000000,
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "embedding"
|
||||
},
|
||||
"voyage/voyage-law-2": {
|
||||
"max_tokens": 16000,
|
||||
"max_input_tokens": 16000,
|
||||
@@ -7719,22 +7735,68 @@
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "embedding"
|
||||
},
|
||||
"voyage/voyage-lite-02-instruct": {
|
||||
"max_tokens": 4000,
|
||||
"max_input_tokens": 4000,
|
||||
"input_cost_per_token": 0.0000001,
|
||||
"voyage/voyage-3-large": {
|
||||
"max_tokens": 32000,
|
||||
"max_input_tokens": 32000,
|
||||
"input_cost_per_token": 0.00000018,
|
||||
"output_cost_per_token": 0.000000,
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "embedding"
|
||||
},
|
||||
"voyage/voyage-finance-2": {
|
||||
"max_tokens": 4000,
|
||||
"max_input_tokens": 4000,
|
||||
"voyage/voyage-3": {
|
||||
"max_tokens": 32000,
|
||||
"max_input_tokens": 32000,
|
||||
"input_cost_per_token": 0.00000006,
|
||||
"output_cost_per_token": 0.000000,
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "embedding"
|
||||
},
|
||||
"voyage/voyage-3-lite": {
|
||||
"max_tokens": 32000,
|
||||
"max_input_tokens": 32000,
|
||||
"input_cost_per_token": 0.00000002,
|
||||
"output_cost_per_token": 0.000000,
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "embedding"
|
||||
},
|
||||
"voyage/voyage-code-3": {
|
||||
"max_tokens": 32000,
|
||||
"max_input_tokens": 32000,
|
||||
"input_cost_per_token": 0.00000018,
|
||||
"output_cost_per_token": 0.000000,
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "embedding"
|
||||
},
|
||||
"voyage/voyage-multimodal-3": {
|
||||
"max_tokens": 32000,
|
||||
"max_input_tokens": 32000,
|
||||
"input_cost_per_token": 0.00000012,
|
||||
"output_cost_per_token": 0.000000,
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "embedding"
|
||||
},
|
||||
"voyage/rerank-2": {
|
||||
"max_tokens": 16000,
|
||||
"max_input_tokens": 16000,
|
||||
"max_output_tokens": 16000,
|
||||
"max_query_tokens": 16000,
|
||||
"input_cost_per_token": 0.00000005,
|
||||
"input_cost_per_query": 0.00000005,
|
||||
"output_cost_per_token": 0.0,
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "rerank"
|
||||
},
|
||||
"voyage/rerank-2-lite": {
|
||||
"max_tokens": 8000,
|
||||
"max_input_tokens": 8000,
|
||||
"max_output_tokens": 8000,
|
||||
"max_query_tokens": 8000,
|
||||
"input_cost_per_token": 0.00000002,
|
||||
"input_cost_per_query": 0.00000002,
|
||||
"output_cost_per_token": 0.0,
|
||||
"litellm_provider": "voyage",
|
||||
"mode": "rerank"
|
||||
},
|
||||
"databricks/databricks-meta-llama-3-1-405b-instruct": {
|
||||
"max_tokens": 128000,
|
||||
"max_input_tokens": 128000,
|
||||
|
||||
Reference in New Issue
Block a user