phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

fix ollama

Browse source
This commit is contained in:
Ishaan Jaff 2024-11-22 17:34:08 -08:00
parent 04dec96f79
commit eabe323eaa
2 changed files with 10 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/llms/ollama.py
View file

@ -14,6 +14,7 @@ import requests # type: ignore
import litellm
from litellm import verbose_logger
from litellm.llms.custom_httpx.http_handler import get_async_httpx_client
from litellm.secret_managers.main import get_secret_str
from litellm.types.utils import ModelInfo, ProviderField, StreamingChoices
@ -456,7 +457,10 @@ def ollama_completion_stream(url, data, logging_obj):
async def ollama_async_streaming(url, data, model_response, encoding, logging_obj):
try:
client = httpx.AsyncClient()
_async_http_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders.OLLAMA
)
client = _async_http_client.client
async with client.stream(
url=f"{url}", json=data, method="POST", timeout=litellm.request_timeout
) as response:

6
litellm/llms/ollama_chat.py
View file

@ -13,6 +13,7 @@ from pydantic import BaseModel
import litellm
from litellm import verbose_logger
from litellm.llms.custom_httpx.http_handler import get_async_httpx_client
from litellm.types.llms.ollama import OllamaToolCall, OllamaToolCallFunction
from litellm.types.llms.openai import ChatCompletionAssistantToolCall
from litellm.types.utils import StreamingChoices
@ -445,7 +446,10 @@ async def ollama_async_streaming(
url, api_key, data, model_response, encoding, logging_obj
):
try:
client = httpx.AsyncClient()
_async_http_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders.OLLAMA
)
client = _async_http_client.client
_request = {
"url": f"{url}",
"json": data,