blob: c503a46a58cb737bb6c1aa46914e012015eeabe7 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
|
from __future__ import annotations
import requests
import os
from ..needs_auth.Openai import Openai
from ...typing import AsyncResult, Messages
class Ollama(Openai):
label = "Ollama"
url = "https://ollama.com"
needs_auth = False
working = True
@classmethod
def get_models(cls):
if not cls.models:
host = os.getenv("OLLAMA_HOST", "127.0.0.1")
port = os.getenv("OLLAMA_PORT", "11434")
url = f"http://{host}:{port}/api/tags"
models = requests.get(url).json()["models"]
cls.models = [model["name"] for model in models]
cls.default_model = cls.models[0]
return cls.models
@classmethod
def create_async_generator(
cls,
model: str,
messages: Messages,
api_base: str = None,
**kwargs
) -> AsyncResult:
if not api_base:
host = os.getenv("OLLAMA_HOST", "localhost")
port = os.getenv("OLLAMA_PORT", "11434")
api_base: str = f"http://{host}:{port}/v1"
return super().create_async_generator(
model, messages, api_base=api_base, **kwargs
)
|
