github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-09-23 12:07:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(llm): Ollama LLM-Embeddings decouple + longer keep_alive settings (#1800)

Browse Source
This commit is contained in:
Robin Boone
2024-04-02 16:23:10 +02:00
committed by GitHub
parent 83adc12a8e
commit b3b0140e24
5 changed files with 33 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
private_gpt/components/embedding/embedding_component.py
View File

@@ -70,7 +70,7 @@ class EmbeddingComponent:
ollama_settings = settings.ollama
self.embedding_model = OllamaEmbedding(
model_name=ollama_settings.embedding_model,
base_url=ollama_settings.api_base,
base_url=ollama_settings.embedding_api_base,
)
case "azopenai":
try:

20
private_gpt/components/llm/llm_component.py
View File

@@ -1,4 +1,6 @@
import logging
from collections.abc import Callable
from typing import Any
from injector import inject, singleton
from llama_index.core.llms import LLM, MockLLM
@@ -133,6 +135,24 @@ class LLMComponent:
additional_kwargs=settings_kwargs,
request_timeout=ollama_settings.request_timeout,
)
if (
ollama_settings.keep_alive
!= ollama_settings.model_fields["keep_alive"].default
):
# Modify Ollama methods to use the "keep_alive" field.
def add_keep_alive(func: Callable[..., Any]) -> Callable[..., Any]:
def wrapper(*args: Any, **kwargs: Any) -> Any:
kwargs["keep_alive"] = ollama_settings.keep_alive
return func(*args, **kwargs)
return wrapper
Ollama.chat = add_keep_alive(Ollama.chat)
Ollama.stream_chat = add_keep_alive(Ollama.stream_chat)
Ollama.complete = add_keep_alive(Ollama.complete)
Ollama.stream_complete = add_keep_alive(Ollama.stream_complete)
case "azopenai":
try:
from llama_index.llms.azure_openai import ( # type: ignore