highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-04-07 11:28:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update docs

Browse Source
This commit is contained in:
ParthSareen 2025-02-04 10:47:32 -08:00
parent 4982089c84
commit 75f88e7aac
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/openai.md
View File

@ -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' }],