westfarn
d1660792ad
Unit Tests / test (push) Successful in 13s
## Summary Implements [chat_backend#6](#6) Part A: - **uv** packaging (`pyproject.toml` + `uv.lock`), Docker/compose (dev + prod), entrypoint/validate-env, Gitea unit-test + auto-deploy workflows (mirror `scha`) - Env-driven Django settings (`DJANGO_*`, `DATABASE_URL`, CSRF/CORS) - **`OLLAMA_BASE_URL`** wired through all Ollama/LangChain clients (prod → `http://10.0.0.128:11434`) - **DatabaseStorage** — prompt/document file blobs in Postgres (`StoredFile`), not container FS; RAG materializes temp paths for loaders - ASGI via `gunicorn` + `UvicornWorker` (HTTP + WebSockets) Companion server-infra PR registers `app_catalog` / `host_apps` (port **8003**). ## Test plan - [ ] `uv sync && cd llm_be && SKIP_RAG_INIT=1 uv run python manage.py test` - [ ] `docker compose build && docker compose up` against bundled Postgres - [ ] Confirm Ollama calls use `OLLAMA_BASE_URL` (not hardcoded localhost) - [ ] Upload a document / prompt file → row in `chat_backend_storedfile`, no disk under `media/` - [ ] After server-infra merge + secret/Postgres/NPM: deploy via `deploy.sh --app chat_backend --env prod`Reviewed-on: #7
34 lines
1.1 KiB
Python
34 lines
1.1 KiB
Python
"""
|
|
llama client - Abstract this in the future
|
|
"""
|
|
|
|
import ollama
|
|
from typing import List, Dict
|
|
from chat_backend.ollama_config import ollama_base_url
|
|
|
|
|
|
class LlamaClient(object):
|
|
def __init__(self, model: str = "llama3"):
|
|
self.client = ollama.Client(host=ollama_base_url())
|
|
self.model = model
|
|
|
|
def check_if_model_exists(self) -> bool:
|
|
raise NotImplementedError
|
|
|
|
def generate_conversation_title(self, message: str):
|
|
response = self.generate_single_message(
|
|
'Summarise the phrase in one to for words"%s"' % message
|
|
)
|
|
|
|
raw_response = response["response"].replace('"', "")
|
|
return " ".join(raw_response.split()[:4])
|
|
|
|
def generate_single_message(self, message: str):
|
|
return self.client.generate(model=self.model, prompt=message)
|
|
|
|
def get_chat_response(self, messages: List[str]):
|
|
return self.client.chat(model=self.model, messages=messages, stream=False)
|
|
|
|
def get_streamed_chat_response(self, messages: List[str]):
|
|
return self.client.chat(model=self.model, messages=messages, stream=True)
|