docs add tg ai rerank docs

This commit is contained in:
Ishaan Jaff 2024-08-27 18:14:40 -07:00
parent 6ce5ba9694
commit 12693e94f1

View file

@ -1,3 +1,6 @@
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
# Together AI
LiteLLM supports all models on Together AI.
@ -204,21 +207,82 @@ print(response)
}
```
## Advanced Usage
Instead of using the `custom_llm_provider` arg to specify which provider you're using (e.g. together ai), you can just pass the provider name as part of the model name, and LiteLLM will parse it out.
## Rerank
Expected format: `<custom_llm_provider>/<model_name>`
### Usage
e.g. completion(model="together_ai/togethercomputer/Llama-2-7B-32K-Instruct", ...)
<Tabs>
<TabItem value="sdk" label="LiteLLM SDK Usage">
```python
from litellm import completion
from litellm import rerank
import os
# set env variable
os.environ["TOGETHERAI_API_KEY"] = ""
os.environ["TOGETHERAI_API_KEY"] = "sk-.."
messages = [{"role": "user", "content": "Write me a poem about the blue sky"}]
query = "What is the capital of the United States?"
documents = [
"Carson City is the capital city of the American state of Nevada.",
"The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
"Washington, D.C. is the capital of the United States.",
"Capital punishment has existed in the United States since before it was a country.",
]
completion(model="together_ai/togethercomputer/Llama-2-7B-32K-Instruct", messages=messages)
```
response = rerank(
model="together_ai/rerank-english-v3.0",
query=query,
documents=documents,
top_n=3,
)
print(response)
```
</TabItem>
<TabItem value="proxy" label="LiteLLM Proxy Usage">
LiteLLM provides an cohere api compatible `/rerank` endpoint for Rerank calls.
**Setup**
Add this to your litellm proxy config.yaml
```yaml
model_list:
- model_name: Salesforce/Llama-Rank-V1
litellm_params:
model: together_ai/Salesforce/Llama-Rank-V1
api_key: os.environ/TOGETHERAI_API_KEY
```
Start litellm
```bash
litellm --config /path/to/config.yaml
# RUNNING on http://0.0.0.0:4000
```
Test request
```bash
curl http://0.0.0.0:4000/rerank \
-H "Authorization: Bearer sk-1234" \
-H "Content-Type: application/json" \
-d '{
"model": "Salesforce/Llama-Rank-V1",
"query": "What is the capital of the United States?",
"documents": [
"Carson City is the capital city of the American state of Nevada.",
"The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
"Washington, D.C. is the capital of the United States.",
"Capital punishment has existed in the United States since before it was a country."
],
"top_n": 3
}'
```
</TabItem>
</Tabs>