github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-09-08 10:39:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(llm): autopull ollama models (#2019)

Browse Source 
* chore: update ollama (llm)

* feat: allow to autopull ollama models

* fix: mypy

* chore: install always ollama client

* refactor: check connection and pull ollama method to utils

* docs: update ollama config with autopulling info
This commit is contained in:
Javier Martinez
2024-07-29 13:25:42 +02:00
committed by GitHub
parent dabf556dae
commit 20bad17c98
8 changed files with 129 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
private_gpt/components/llm/llm_component.py
View File

@@ -146,8 +146,15 @@ class LLMComponent:
"repeat_penalty": ollama_settings.repeat_penalty, # ollama llama-cpp
}
self.llm = Ollama(
model=ollama_settings.llm_model,
# calculate llm model. If not provided tag, it will be use latest
model_name = (
ollama_settings.llm_model + ":latest"
if ":" not in ollama_settings.llm_model
else ollama_settings.llm_model
)
llm = Ollama(
model=model_name,
base_url=ollama_settings.api_base,
temperature=settings.llm.temperature,
context_window=settings.llm.context_window,
@@ -155,6 +162,16 @@ class LLMComponent:
request_timeout=ollama_settings.request_timeout,
)
if ollama_settings.autopull_models:
from private_gpt.utils.ollama import check_connection, pull_model
if not check_connection(llm.client):
raise ValueError(
f"Failed to connect to Ollama, "
f"check if Ollama server is running on {ollama_settings.api_base}"
)
pull_model(llm.client, model_name)
if (
ollama_settings.keep_alive
!= ollama_settings.model_fields["keep_alive"].default
@@ -172,6 +189,8 @@ class LLMComponent:
Ollama.complete = add_keep_alive(Ollama.complete)
Ollama.stream_complete = add_keep_alive(Ollama.stream_complete)
self.llm = llm
case "azopenai":
try:
from llama_index.llms.azure_openai import ( # type: ignore