|
@@ -94,12 +94,11 @@ except Exception as e:
|
|
|
print(f"Error: {e}")
|
|
|
```
|
|
|
|
|
|
-#### Experimental
|
|
|
+#### Extra Arguments
|
|
|
|
|
|
- `num_ctx` parameter can be used to set the context window for the model
|
|
|
- OpenAI Python SDK does not support setting context window size, however this can be set for Ollama through the `extra_body` parameter
|
|
|
|
|
|
-- The recommended way to control this is through the [Ollama Python SDK](https://github.com/ollama/ollama-python) with the `options` parameter
|
|
|
```py
|
|
|
completion = client.beta.chat.completions.create(
|
|
|
model="llama3.1:8b",
|
|
@@ -156,12 +155,11 @@ const embedding = await openai.embeddings.create({
|
|
|
})
|
|
|
```
|
|
|
|
|
|
-#### Experimental
|
|
|
+#### Extra Arguments
|
|
|
|
|
|
- `num_ctx` parameter can be used to set the context window for the model
|
|
|
- OpenAI JS SDK does not support setting context window size, however this can be set for Ollama by passing `num_ctx` directly with a `@ts-expect-error` as an undocumented parameter in the [OpenAI JS SDK](https://github.com/openai/openai-node?tab=readme-ov-file#making-customundocumented-requests)
|
|
|
|
|
|
-- The recommended way to control this is through the [Ollama JS SDK](https://github.com/ollama/ollama-js) with the `options` parameter
|
|
|
```js
|
|
|
const chatCompletion = await openai.chat.completions.create({
|
|
|
messages: [{ role: 'user', content: 'Say this is a test' }],
|