scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 83

docs(perplexity.md): removing return_citations documentation (#8527)

Browse source 
Deprecation Notice:

Effective immediately, all API users will see citations returned as part of their requests by default. This is not a breaking change. The return_citations parameter will no longer have any effect.

[source](https://docs.perplexity.ai/changelog/changelog#citations-public-release-and-increased-default-rate-limits)
This commit is contained in:
miraclebakelaser 2025-02-14 15:09:54 +09:00 • committed by GitHub
parent cd9bc7726b
commit 3c197b9925
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 65 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

66
docs/my-website/docs/providers/perplexity.md
View file

@ -64,71 +64,7 @@ All models listed here https://docs.perplexity.ai/docs/model-cards are supported
## Return citations
Perplexity supports returning citations via `return_citations=True`. [Perplexity Docs](https://docs.perplexity.ai/reference/post_chat_completions). Note: Perplexity has this feature in **closed beta**, so you need them to grant you access to get citations from their API.
If perplexity returns citations, LiteLLM will pass it straight through.
:::info
For passing more provider-specific, [go here](../completion/provider_specific_params.md)
For more information about passing provider-specific parameters, [go here](../completion/provider_specific_params.md)
:::
<Tabs>
<TabItem value="sdk" label="SDK">
```python
from litellm import completion
import os
os.environ['PERPLEXITYAI_API_KEY'] = ""
response = completion(
model="perplexity/mistral-7b-instruct",
messages=messages,
return_citations=True
)
print(response)
```
</TabItem>
<TabItem value="proxy" label="PROXY">
1. Add perplexity to config.yaml
```yaml
model_list:
- model_name: "perplexity-model"
litellm_params:
model: "llama-3.1-sonar-small-128k-online"
api_key: os.environ/PERPLEXITY_API_KEY
```
2. Start proxy
```bash
litellm --config /path/to/config.yaml
```
3. Test it!
```bash
curl -L -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
"model": "perplexity-model",
"messages": [
{
"role": "user",
"content": "Who won the world cup in 2022?"
}
],
"return_citations": true
}'
```
[**Call w/ OpenAI SDK, Langchain, Instructor, etc.**](../proxy/user_keys.md#chatcompletions)
</TabItem>
</Tabs>