mirror of
https://github.com/OneUptime/oneuptime.git
synced 2026-04-06 00:32:12 +02:00
refactor: remove LLM-related Docker workflows and associated files
This commit is contained in:
Nawaz Dhandala
101
.github/workflows/release.yml
vendored
101
.github/workflows/release.yml
vendored
@@ -1647,101 +1647,6 @@ jobs:
|
||||
run: bash ./Scripts/NPM/PublishAllPackages.sh
|
||||
|
||||
|
||||
llm-docker-image-deploy:
|
||||
needs: [generate-build-number, read-version]
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
|
||||
# Docker compose needs a lot of space to build images, so we need to free up some space first in the GitHub Actions runner
|
||||
- name: Free Disk Space (Ubuntu)
|
||||
uses: jlumbroso/free-disk-space@main
|
||||
with:
|
||||
# this might remove tools that are actually needed,
|
||||
# if set to "true" but frees about 6 GB
|
||||
tool-cache: false
|
||||
android: true
|
||||
dotnet: true
|
||||
haskell: true
|
||||
large-packages: true
|
||||
docker-images: true
|
||||
swap-storage: true
|
||||
|
||||
- name: Docker Meta
|
||||
id: meta
|
||||
uses: docker/metadata-action@v4
|
||||
with:
|
||||
images: |
|
||||
oneuptime/llm
|
||||
ghcr.io/oneuptime/llm
|
||||
tags: |
|
||||
type=raw,value=release,enable=true
|
||||
type=semver,value=${{needs.read-version.outputs.major_minor}},pattern={{version}},enable=true
|
||||
|
||||
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ github.ref }}
|
||||
|
||||
- uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: latest
|
||||
|
||||
# - name: Setup Git LFS
|
||||
# run: git lfs install
|
||||
|
||||
# # Cannot do this, no space on the gitHub standard runner. We need to use the large runner which is selfhosted
|
||||
# - name: Download the Model from Hugging Face
|
||||
# run: mkdir -p ./LLM/Models && cd ./LLM/Models && git clone https://${{ secrets.HUGGING_FACE_USERNAME }}:${{ secrets.HUGGING_FACE_PASSWORD }}@huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
||||
|
||||
- name: Set up QEMU
|
||||
uses: docker/setup-qemu-action@v3
|
||||
with:
|
||||
image: tonistiigi/binfmt:qemu-v10.0.4
|
||||
|
||||
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Generate Dockerfile from Dockerfile.tpl
|
||||
uses: nick-fields/retry@v3
|
||||
with:
|
||||
timeout_minutes: 10
|
||||
max_attempts: 3
|
||||
command: npm run prerun
|
||||
|
||||
# Build and deploy nginx.
|
||||
|
||||
- name: Login to Docker Hub
|
||||
uses: nick-fields/retry@v3
|
||||
with:
|
||||
timeout_minutes: 5
|
||||
max_attempts: 3
|
||||
command: |
|
||||
echo "${{ secrets.DOCKERHUB_PASSWORD }}" | docker login --username "${{ secrets.DOCKERHUB_USERNAME }}" --password-stdin
|
||||
|
||||
- name: Login to GitHub Container Registry
|
||||
uses: nick-fields/retry@v3
|
||||
with:
|
||||
timeout_minutes: 5
|
||||
max_attempts: 3
|
||||
command: |
|
||||
echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io --username "${{ github.repository_owner }}" --password-stdin
|
||||
|
||||
- name: Build and push
|
||||
uses: nick-fields/retry@v3
|
||||
with:
|
||||
timeout_minutes: 45
|
||||
max_attempts: 3
|
||||
command: |
|
||||
bash ./Scripts/GHA/build_docker_images.sh \
|
||||
--image llm \
|
||||
--version "${{needs.read-version.outputs.major_minor}}" \
|
||||
--dockerfile ./LLM/Dockerfile \
|
||||
--context ./LLM \
|
||||
--platforms linux/amd64 \
|
||||
--git-sha "${{ github.sha }}"
|
||||
|
||||
docs-docker-image-deploy:
|
||||
needs: [generate-build-number, read-version]
|
||||
runs-on: ubuntu-latest
|
||||
@@ -2131,7 +2036,6 @@ jobs:
|
||||
- app-docker-image-deploy
|
||||
- copilot-docker-image-deploy
|
||||
- accounts-docker-image-deploy
|
||||
- llm-docker-image-deploy
|
||||
- docs-docker-image-deploy
|
||||
- worker-docker-image-deploy
|
||||
- workflow-docker-image-deploy
|
||||
@@ -2162,7 +2066,6 @@ jobs:
|
||||
"app",
|
||||
"copilot",
|
||||
"accounts",
|
||||
"llm",
|
||||
"docs",
|
||||
"worker",
|
||||
"workflow",
|
||||
@@ -2221,7 +2124,7 @@ jobs:
|
||||
|
||||
test-e2e-release-saas:
|
||||
runs-on: ubuntu-latest
|
||||
needs: [telemetry-docker-image-deploy, publish-mcp-server, copilot-docker-image-deploy, docs-docker-image-deploy, api-reference-docker-image-deploy, workflow-docker-image-deploy, llm-docker-image-deploy, accounts-docker-image-deploy, admin-dashboard-docker-image-deploy, app-docker-image-deploy, dashboard-docker-image-deploy, probe-ingest-docker-image-deploy, server-monitor-ingest-docker-image-deploy, isolated-vm-docker-image-deploy, home-docker-image-deploy, worker-docker-image-deploy, otel-collector-docker-image-deploy, probe-docker-image-deploy, status-page-docker-image-deploy, test-docker-image-deploy, test-server-docker-image-deploy, publish-npm-packages, e2e-docker-image-deploy, helm-chart-deploy, generate-build-number, read-version, nginx-docker-image-deploy, incoming-request-ingest-docker-image-deploy]
|
||||
needs: [telemetry-docker-image-deploy, publish-mcp-server, copilot-docker-image-deploy, docs-docker-image-deploy, api-reference-docker-image-deploy, workflow-docker-image-deploy, accounts-docker-image-deploy, admin-dashboard-docker-image-deploy, app-docker-image-deploy, dashboard-docker-image-deploy, probe-ingest-docker-image-deploy, server-monitor-ingest-docker-image-deploy, isolated-vm-docker-image-deploy, home-docker-image-deploy, worker-docker-image-deploy, otel-collector-docker-image-deploy, probe-docker-image-deploy, status-page-docker-image-deploy, test-docker-image-deploy, test-server-docker-image-deploy, publish-npm-packages, e2e-docker-image-deploy, helm-chart-deploy, generate-build-number, read-version, nginx-docker-image-deploy, incoming-request-ingest-docker-image-deploy]
|
||||
env:
|
||||
CI_PIPELINE_ID: ${{github.run_number}}
|
||||
steps:
|
||||
@@ -2309,7 +2212,7 @@ jobs:
|
||||
test-e2e-release-self-hosted:
|
||||
runs-on: ubuntu-latest
|
||||
# After all the jobs runs
|
||||
needs: [telemetry-docker-image-deploy, publish-mcp-server, copilot-docker-image-deploy, incoming-request-ingest-docker-image-deploy, docs-docker-image-deploy, api-reference-docker-image-deploy, workflow-docker-image-deploy, llm-docker-image-deploy, accounts-docker-image-deploy, admin-dashboard-docker-image-deploy, app-docker-image-deploy, dashboard-docker-image-deploy, probe-ingest-docker-image-deploy, server-monitor-ingest-docker-image-deploy, isolated-vm-docker-image-deploy, home-docker-image-deploy, worker-docker-image-deploy, otel-collector-docker-image-deploy, probe-docker-image-deploy, status-page-docker-image-deploy, test-docker-image-deploy, test-server-docker-image-deploy, publish-npm-packages, e2e-docker-image-deploy, helm-chart-deploy, generate-build-number, read-version, nginx-docker-image-deploy]
|
||||
needs: [telemetry-docker-image-deploy, publish-mcp-server, copilot-docker-image-deploy, incoming-request-ingest-docker-image-deploy, docs-docker-image-deploy, api-reference-docker-image-deploy, workflow-docker-image-deploy, accounts-docker-image-deploy, admin-dashboard-docker-image-deploy, app-docker-image-deploy, dashboard-docker-image-deploy, probe-ingest-docker-image-deploy, server-monitor-ingest-docker-image-deploy, isolated-vm-docker-image-deploy, home-docker-image-deploy, worker-docker-image-deploy, otel-collector-docker-image-deploy, probe-docker-image-deploy, status-page-docker-image-deploy, test-docker-image-deploy, test-server-docker-image-deploy, publish-npm-packages, e2e-docker-image-deploy, helm-chart-deploy, generate-build-number, read-version, nginx-docker-image-deploy]
|
||||
env:
|
||||
CI_PIPELINE_ID: ${{github.run_number}}
|
||||
steps:
|
||||
|
||||
99
.github/workflows/test-release.yaml
vendored
99
.github/workflows/test-release.yaml
vendored
@@ -207,103 +207,6 @@ jobs:
|
||||
|
||||
|
||||
|
||||
llm-docker-image-deploy:
|
||||
needs: [read-version, generate-build-number]
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
|
||||
# Docker compose needs a lot of space to build images, so we need to free up some space first in the GitHub Actions runner
|
||||
- name: Free Disk Space (Ubuntu)
|
||||
uses: jlumbroso/free-disk-space@main
|
||||
with:
|
||||
# this might remove tools that are actually needed,
|
||||
# if set to "true" but frees about 6 GB
|
||||
tool-cache: false
|
||||
android: true
|
||||
dotnet: true
|
||||
haskell: true
|
||||
large-packages: true
|
||||
docker-images: true
|
||||
swap-storage: true
|
||||
|
||||
- name: Docker Meta
|
||||
id: meta
|
||||
uses: docker/metadata-action@v4
|
||||
with:
|
||||
images: |
|
||||
oneuptime/llm
|
||||
ghcr.io/oneuptime/llm
|
||||
tags: |
|
||||
type=raw,value=test,enable=true
|
||||
type=raw,value=${{needs.read-version.outputs.major_minor}}-test,enable=true
|
||||
|
||||
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ github.ref }}
|
||||
|
||||
- uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: latest
|
||||
|
||||
# - name: Setup Git LFS
|
||||
# run: git lfs install
|
||||
|
||||
# # Cannot do this, no space on the gitHub standard runner. We need to use the large runner which is selfhosted
|
||||
# - name: Download the Model from Hugging Face
|
||||
# run: mkdir -p ./LLM/Models && cd ./LLM/Models && git clone https://${{ secrets.HUGGING_FACE_USERNAME }}:${{ secrets.HUGGING_FACE_PASSWORD }}@huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
||||
|
||||
- name: Set up QEMU
|
||||
uses: docker/setup-qemu-action@v3
|
||||
with:
|
||||
image: tonistiigi/binfmt:qemu-v10.0.4
|
||||
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Generate Dockerfile from Dockerfile.tpl
|
||||
uses: nick-fields/retry@v3
|
||||
with:
|
||||
timeout_minutes: 10
|
||||
max_attempts: 3
|
||||
command: npm run prerun
|
||||
|
||||
# Build and deploy nginx.
|
||||
|
||||
- name: Login to Docker Hub
|
||||
uses: nick-fields/retry@v3
|
||||
with:
|
||||
timeout_minutes: 5
|
||||
max_attempts: 3
|
||||
command: |
|
||||
echo "${{ secrets.DOCKERHUB_PASSWORD }}" | docker login --username "${{ secrets.DOCKERHUB_USERNAME }}" --password-stdin
|
||||
|
||||
- name: Login to GitHub Container Registry
|
||||
uses: nick-fields/retry@v3
|
||||
with:
|
||||
timeout_minutes: 5
|
||||
max_attempts: 3
|
||||
command: |
|
||||
echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io --username "${{ github.repository_owner }}" --password-stdin
|
||||
|
||||
- name: Build and push
|
||||
uses: nick-fields/retry@v3
|
||||
with:
|
||||
timeout_minutes: 30
|
||||
max_attempts: 3
|
||||
command: |
|
||||
bash ./Scripts/GHA/build_docker_images.sh \
|
||||
--image llm \
|
||||
--version "${{needs.read-version.outputs.major_minor}}-test" \
|
||||
--dockerfile ./LLM/Dockerfile \
|
||||
--context ./LLM \
|
||||
--platforms linux/amd64 \
|
||||
--git-sha "${{ github.sha }}" \
|
||||
--extra-tags test \
|
||||
--extra-enterprise-tags enterprise-test
|
||||
|
||||
|
||||
nginx-docker-image-deploy:
|
||||
needs: [read-version, generate-build-number]
|
||||
runs-on: ubuntu-latest
|
||||
@@ -1965,7 +1868,7 @@ jobs:
|
||||
|
||||
test-helm-chart:
|
||||
runs-on: ubuntu-latest
|
||||
needs: [infrastructure-agent-deploy, publish-mcp-server, llm-docker-image-deploy, publish-terraform-provider, telemetry-docker-image-deploy, copilot-docker-image-deploy, docs-docker-image-deploy, worker-docker-image-deploy, workflow-docker-image-deploy, isolated-vm-docker-image-deploy, home-docker-image-deploy, api-reference-docker-image-deploy, test-server-docker-image-deploy, test-docker-image-deploy, probe-ingest-docker-image-deploy, server-monitor-ingest-docker-image-deploy, probe-docker-image-deploy, dashboard-docker-image-deploy, admin-dashboard-docker-image-deploy, app-docker-image-deploy, accounts-docker-image-deploy, otel-collector-docker-image-deploy, status-page-docker-image-deploy, nginx-docker-image-deploy, e2e-docker-image-deploy, incoming-request-ingest-docker-image-deploy]
|
||||
needs: [infrastructure-agent-deploy, publish-mcp-server, publish-terraform-provider, telemetry-docker-image-deploy, copilot-docker-image-deploy, docs-docker-image-deploy, worker-docker-image-deploy, workflow-docker-image-deploy, isolated-vm-docker-image-deploy, home-docker-image-deploy, api-reference-docker-image-deploy, test-server-docker-image-deploy, test-docker-image-deploy, probe-ingest-docker-image-deploy, server-monitor-ingest-docker-image-deploy, probe-docker-image-deploy, dashboard-docker-image-deploy, admin-dashboard-docker-image-deploy, app-docker-image-deploy, accounts-docker-image-deploy, otel-collector-docker-image-deploy, status-page-docker-image-deploy, nginx-docker-image-deploy, e2e-docker-image-deploy, incoming-request-ingest-docker-image-deploy]
|
||||
env:
|
||||
CI_PIPELINE_ID: ${{github.run_number}}
|
||||
steps:
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
Models/*
|
||||
@@ -1,20 +0,0 @@
|
||||
# Use an official Python runtime as a parent image
|
||||
FROM huggingface/transformers-pytorch-gpu:latest
|
||||
|
||||
ARG IS_ENTERPRISE_EDITION=false
|
||||
ENV IS_ENTERPRISE_EDITION=${IS_ENTERPRISE_EDITION}
|
||||
|
||||
# Set the working directory in the container to /app
|
||||
WORKDIR /app
|
||||
|
||||
# Copy the current directory contents into the container at /app
|
||||
ADD . /app
|
||||
|
||||
# Install any needed packages specified in requirements.txt
|
||||
RUN pip install --no-cache-dir -r requirements.txt
|
||||
|
||||
# Make port 8547 available to the world outside this container
|
||||
EXPOSE 8547
|
||||
|
||||
# Run app.py when the container launches
|
||||
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8547" ]
|
||||
@@ -1,81 +0,0 @@
|
||||
# LLM
|
||||
|
||||
### Development Guide
|
||||
|
||||
#### Step 1: Downloading Model from Hugging Face
|
||||
|
||||
Please make sure you have git lfs installed before cloning the model.
|
||||
|
||||
```bash
|
||||
git lfs install
|
||||
```
|
||||
|
||||
```bash
|
||||
cd ./LLM/Models
|
||||
# Here we are downloading the Meta-Llama-3-8B-Instruct model
|
||||
git clone https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
||||
```
|
||||
|
||||
You will be asked for username and password.
|
||||
Please use Hugging Face Username as Username and,
|
||||
Hugging Face API Token as Password.
|
||||
|
||||
#### Step 2: Install Docker.
|
||||
|
||||
Install Docker and Docker Compose
|
||||
|
||||
```bash
|
||||
sudo apt-get update
|
||||
sudo curl -sSL https://get.docker.com/ | sh
|
||||
```
|
||||
|
||||
Install Rootless Docker
|
||||
|
||||
```bash
|
||||
sudo apt-get install -y uidmap
|
||||
dockerd-rootless-setuptool.sh install
|
||||
```
|
||||
|
||||
See if the installation works
|
||||
|
||||
```bash
|
||||
docker --version
|
||||
docker ps
|
||||
|
||||
# You should see no containers running, but you should not see any errors.
|
||||
```
|
||||
|
||||
#### Step 3: Insall nvidia drivers on the machine to use GPU
|
||||
|
||||
- Install Container Toolkit: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html#installing-the-nvidia-container-toolkit
|
||||
- Install CUDA: https://developer.nvidia.com/cuda-downloads?target_os=Linux&target_arch=x86_64&Distribution=Ubuntu&target_version=22.04&target_type=deb_network
|
||||
- Restart the machine
|
||||
- You should now see GPU when you run `nvidia-smi`
|
||||
|
||||
#### Step 4: Run the test workload to see if GPU is connected to Docker.
|
||||
|
||||
```bash
|
||||
docker run --rm -it --gpus=all nvcr.io/nvidia/k8s/cuda-sample:nbody nbody -gpu -benchmark
|
||||
```
|
||||
|
||||
You have configured the machine to use GPU with Docker.
|
||||
|
||||
|
||||
### Build
|
||||
|
||||
- Download models from meta
|
||||
- Once the model is downloaded, place them in the `Llama/Models` folder. Please make sure you also place tokenizer.model and tokenizer_checklist.chk in the same folder.
|
||||
- Edit `Dockerfile` to include the model name in the `MODEL_NAME` variable.
|
||||
- Docker build
|
||||
|
||||
```
|
||||
npm run build-ai
|
||||
```
|
||||
|
||||
### Run
|
||||
|
||||
```
|
||||
npm run start-ai
|
||||
```
|
||||
|
||||
After you start, run `nvidia-smi` to see if the GPU is being used. You should see the python process running on the GPU.
|
||||
227
LLM/app.py
227
LLM/app.py
@@ -1,227 +0,0 @@
|
||||
import uuid
|
||||
import transformers
|
||||
import asyncio
|
||||
import os
|
||||
import torch
|
||||
import aiohttp
|
||||
from fastapi import FastAPI
|
||||
from pydantic import BaseModel
|
||||
from contextlib import asynccontextmanager
|
||||
from apscheduler.schedulers.background import BackgroundScheduler
|
||||
|
||||
# ENV VARS
|
||||
ONEUPTIME_URL = os.getenv("ONEUPTIME_URL")
|
||||
HF_MODEL_NAME = os.getenv("HF_MODEL_NAME")
|
||||
HF_TOKEN = os.getenv("HF_TOKEN")
|
||||
|
||||
if not HF_MODEL_NAME:
|
||||
HF_MODEL_NAME = "meta-llama/Meta-Llama-3-8B-Instruct"
|
||||
print(f"HF_MODEL_NAME not set. Using default model: {HF_MODEL_NAME}")
|
||||
|
||||
if not ONEUPTIME_URL:
|
||||
ONEUPTIME_URL = "https://oneuptime.com"
|
||||
|
||||
if not HF_TOKEN:
|
||||
# Print error and exit
|
||||
print("HF_TOKEN env var is required. This is the Hugging Face API token. You can get it from https://huggingface.co/account/overview. Exiting..")
|
||||
exit()
|
||||
|
||||
# TODO: Store this in redis down the line.
|
||||
items_pending = {}
|
||||
items_processed = {}
|
||||
errors = {}
|
||||
|
||||
async def validateSecretKey(secretKey):
|
||||
try:
|
||||
|
||||
# If no secret key then return false
|
||||
if not secretKey:
|
||||
return False
|
||||
|
||||
async with aiohttp.ClientSession() as session:
|
||||
print(f"Validating secret key")
|
||||
url = f"{ONEUPTIME_URL}/api/copilot-code-repository/is-valid/{secretKey}"
|
||||
async with session.get(url) as response:
|
||||
print(response)
|
||||
if response.status == 200:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
print(repr(e))
|
||||
return False
|
||||
|
||||
async def job(queue):
|
||||
print("Downlaoding model from Hugging Face: "+HF_MODEL_NAME)
|
||||
|
||||
# check if the model is meta-llama/Meta-Llama-3-8B-Instruct
|
||||
if HF_MODEL_NAME == "meta-llama/Meta-Llama-3-8B-Instruct":
|
||||
print("If you want to use a different model, please set the HF_MODEL_NAME environment variable.")
|
||||
|
||||
print("This may take a while (minutes or sometimes hours) depending on the model size.")
|
||||
|
||||
# model_path = "/app/Models/Meta-Llama-3-8B-Instruct"
|
||||
model_path = HF_MODEL_NAME
|
||||
|
||||
pipe = transformers.pipeline(
|
||||
"text-generation",
|
||||
model=model_path,
|
||||
# use gpu if available
|
||||
device="cuda" if torch.cuda.is_available() else "cpu",
|
||||
# max_new_tokens=8096
|
||||
)
|
||||
|
||||
|
||||
print("Model downloaded.")
|
||||
|
||||
while True:
|
||||
|
||||
random_id = None
|
||||
|
||||
try:
|
||||
# process this item.
|
||||
random_id = await queue.get()
|
||||
print(f"Processing item {random_id}")
|
||||
messages = items_pending[random_id]
|
||||
print(f"Messages:")
|
||||
print(messages)
|
||||
outputs = pipe(messages)
|
||||
items_processed[random_id] = outputs
|
||||
del items_pending[random_id]
|
||||
print(f"Processed item {random_id}")
|
||||
except Exception as e:
|
||||
print(f"Error processing item {random_id}")
|
||||
# store error
|
||||
errors[random_id] = repr(e)
|
||||
# delete from items_pending
|
||||
if random_id in items_pending:
|
||||
del items_pending[random_id]
|
||||
print(e)
|
||||
|
||||
|
||||
|
||||
|
||||
@asynccontextmanager
|
||||
async def lifespan(app:FastAPI):
|
||||
queue = asyncio.Queue()
|
||||
app.model_queue = queue
|
||||
asyncio.create_task(job(queue))
|
||||
yield
|
||||
|
||||
# Declare a Pydantic model for the request body
|
||||
class Prompt(BaseModel):
|
||||
messages: list
|
||||
# secretkey: str
|
||||
|
||||
# Declare a Pydantic model for the request body
|
||||
class PromptResult(BaseModel):
|
||||
id: str
|
||||
# secretkey: str
|
||||
|
||||
app = FastAPI(lifespan=lifespan)
|
||||
|
||||
@app.get("/")
|
||||
async def root():
|
||||
return {"status": "ok"}
|
||||
|
||||
@app.get("/status")
|
||||
async def status():
|
||||
return {"status": "ok"}
|
||||
|
||||
@app.post("/prompt/")
|
||||
async def create_item(prompt: Prompt):
|
||||
|
||||
try:
|
||||
# If not prompt then return bad request error
|
||||
if not prompt:
|
||||
return {"error": "Prompt is required"}
|
||||
|
||||
# Validate the secret key
|
||||
# is_valid = await validateSecretKey(prompt.secretkey)
|
||||
|
||||
# if not is_valid:
|
||||
# print("Invalid secret key")
|
||||
# return {"error": "Invalid secret key"}
|
||||
|
||||
# messages are in str format. We need to convert them fron json [] to list
|
||||
messages = prompt.messages
|
||||
|
||||
# Log prompt to console
|
||||
print(messages)
|
||||
|
||||
# Generate UUID
|
||||
random_id = str(uuid.uuid4())
|
||||
|
||||
# add to queue
|
||||
|
||||
items_pending[random_id] = messages
|
||||
await app.model_queue.put(random_id)
|
||||
|
||||
# Return response
|
||||
return {
|
||||
"id": random_id,
|
||||
"status": "queued"
|
||||
}
|
||||
except Exception as e:
|
||||
print(e)
|
||||
return {"error": repr(e)}
|
||||
|
||||
# Disable this API in production
|
||||
@app.get("/queue-status/")
|
||||
async def queue_status():
|
||||
try:
|
||||
return {"pending": items_pending, "processed": items_processed, "queue": app.model_queue.qsize(), "errors": errors}
|
||||
except Exception as e:
|
||||
print(e)
|
||||
return {"error": repr(e)}
|
||||
|
||||
@app.post("/prompt-result/")
|
||||
async def prompt_status(prompt_status: PromptResult):
|
||||
try:
|
||||
# Log prompt status to console
|
||||
print(prompt_status)
|
||||
|
||||
# Validate the secret key
|
||||
# is_valid = await validateSecretKey(prompt_status.secretkey)
|
||||
|
||||
# if not is_valid:
|
||||
# print("Invalid secret key")
|
||||
# return {"error": "Invalid secret key"}
|
||||
|
||||
# If not prompt status then return bad request error
|
||||
if not prompt_status:
|
||||
return {"error": "Prompt status is required"}
|
||||
|
||||
# check if item is processed.
|
||||
if prompt_status.id in items_processed:
|
||||
|
||||
|
||||
return_value = {
|
||||
"id": prompt_status.id,
|
||||
"status": "processed",
|
||||
"output": items_processed[prompt_status.id]
|
||||
}
|
||||
|
||||
# delete from item_processed
|
||||
del items_processed[prompt_status.id]
|
||||
|
||||
return return_value
|
||||
else:
|
||||
|
||||
status = "not found"
|
||||
|
||||
if prompt_status.id in items_pending:
|
||||
status = "pending"
|
||||
|
||||
return {
|
||||
"id": prompt_status.id,
|
||||
"status": status
|
||||
}
|
||||
except Exception as e:
|
||||
print(e)
|
||||
return {"error": repr(e)}
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,11 +0,0 @@
|
||||
# Hugging Face Transformers
|
||||
transformers==4.41.2
|
||||
|
||||
# Rest api related stuff.
|
||||
fastapi===0.109.1
|
||||
uvicorn===0.23.2
|
||||
pydantic===2.4.2
|
||||
|
||||
# Rest of the app
|
||||
APScheduler===3.10.4
|
||||
aiohttp===3.9.5
|
||||
@@ -1,112 +0,0 @@
|
||||
{
|
||||
"ts-node": {
|
||||
// these options are overrides used only by ts-node
|
||||
// same as the --compilerOptions flag and the TS_NODE_COMPILER_OPTIONS environment variable
|
||||
"compilerOptions": {
|
||||
"module": "commonjs",
|
||||
"resolveJsonModule": true,
|
||||
}
|
||||
},
|
||||
"compilerOptions": {
|
||||
/* Visit https://aka.ms/tsconfig.json to read more about this file */
|
||||
|
||||
/* Projects */
|
||||
// "incremental": true, /* Enable incremental compilation */
|
||||
// "composite": true, /* Enable constraints that allow a TypeScript project to be used with project references. */
|
||||
// "tsBuildInfoFile": "./", /* Specify the folder for .tsbuildinfo incremental compilation files. */
|
||||
// "disableSourceOfProjectReferenceRedirect": true, /* Disable preferring source files instead of declaration files when referencing composite projects */
|
||||
// "disableSolutionSearching": true, /* Opt a project out of multi-project reference checking when editing. */
|
||||
// "disableReferencedProjectLoad": true, /* Reduce the number of projects loaded automatically by TypeScript. */
|
||||
"module": "ES2020",
|
||||
/* Language and Environment */
|
||||
"target": "es2020" /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */,
|
||||
// "lib": [], /* Specify a set of bundled library declaration files that describe the target runtime environment. */
|
||||
"jsx": "react" /* Specify what JSX code is generated. */,
|
||||
"experimentalDecorators": true, /* Enable experimental support for TC39 stage 2 draft decorators. */
|
||||
"emitDecoratorMetadata": true, /* Emit design-type metadata for decorated declarations in source files. */
|
||||
// "jsxFactory": "", /* Specify the JSX factory function used when targeting React JSX emit, e.g. 'React.createElement' or 'h' */
|
||||
// "jsxFragmentFactory": "", /* Specify the JSX Fragment reference used for fragments when targeting React JSX emit e.g. 'React.Fragment' or 'Fragment'. */
|
||||
// "jsxImportSource": "", /* Specify module specifier used to import the JSX factory functions when using `jsx: react-jsx*`.` */
|
||||
// "reactNamespace": "", /* Specify the object invoked for `createElement`. This only applies when targeting `react` JSX emit. */
|
||||
// "noLib": true, /* Disable including any library files, including the default lib.d.ts. */
|
||||
// "useDefineForClassFields": true, /* Emit ECMAScript-standard-compliant class fields. */
|
||||
|
||||
/* Modules */
|
||||
// "module": "es2022" /* Specify what module code is generated. */,
|
||||
// "rootDir": "./", /* Specify the root folder within your source files. */
|
||||
"moduleResolution": "node", /* Specify how TypeScript looks up a file from a given module specifier. */
|
||||
// "baseUrl": "./", /* Specify the base directory to resolve non-relative module names. */
|
||||
// "paths": {}, /* Specify a set of entries that re-map imports to additional lookup locations. */
|
||||
// "rootDirs": [], /* Allow multiple folders to be treated as one when resolving modules. */
|
||||
"typeRoots": [
|
||||
"./node_modules/@types"
|
||||
], /* Specify multiple folders that act like `./node_modules/@types`. */
|
||||
"types": ["node"], /* Specify type package names to be included without being referenced in a source file. */
|
||||
// "allowUmdGlobalAccess": true, /* Allow accessing UMD globals from modules. */
|
||||
// "resolveJsonModule": true, /* Enable importing .json files */
|
||||
// "noResolve": true, /* Disallow `import`s, `require`s or `<reference>`s from expanding the number of files TypeScript should add to a project. */
|
||||
|
||||
/* JavaScript Support */
|
||||
// "allowJs": true, /* Allow JavaScript files to be a part of your program. Use the `checkJS` option to get errors from these files. */
|
||||
// "checkJs": true, /* Enable error reporting in type-checked JavaScript files. */
|
||||
// "maxNodeModuleJsDepth": 1, /* Specify the maximum folder depth used for checking JavaScript files from `node_modules`. Only applicable with `allowJs`. */
|
||||
|
||||
/* Emit */
|
||||
// "declaration": true, /* Generate .d.ts files from TypeScript and JavaScript files in your project. */
|
||||
// "declarationMap": true, /* Create sourcemaps for d.ts files. */
|
||||
// "emitDeclarationOnly": true, /* Only output d.ts files and not JavaScript files. */
|
||||
"sourceMap": true, /* Create source map files for emitted JavaScript files. */
|
||||
// "outFile": "./", /* Specify a file that bundles all outputs into one JavaScript file. If `declaration` is true, also designates a file that bundles all .d.ts output. */
|
||||
"outDir": "./build/dist", /* Specify an output folder for all emitted files. */
|
||||
// "removeComments": true, /* Disable emitting comments. */
|
||||
// "noEmit": true, /* Disable emitting files from a compilation. */
|
||||
// "importHelpers": true, /* Allow importing helper functions from tslib once per project, instead of including them per-file. */
|
||||
// "importsNotUsedAsValues": "remove", /* Specify emit/checking behavior for imports that are only used for types */
|
||||
// "downlevelIteration": true, /* Emit more compliant, but verbose and less performant JavaScript for iteration. */
|
||||
// "sourceRoot": "", /* Specify the root path for debuggers to find the reference source code. */
|
||||
// "mapRoot": "", /* Specify the location where debugger should locate map files instead of generated locations. */
|
||||
// "inlineSourceMap": true, /* Include sourcemap files inside the emitted JavaScript. */
|
||||
// "inlineSources": true, /* Include source code in the sourcemaps inside the emitted JavaScript. */
|
||||
// "emitBOM": true, /* Emit a UTF-8 Byte Order Mark (BOM) in the beginning of output files. */
|
||||
// "newLine": "crlf", /* Set the newline character for emitting files. */
|
||||
// "stripInternal": true, /* Disable emitting declarations that have `@internal` in their JSDoc comments. */
|
||||
// "noEmitHelpers": true, /* Disable generating custom helper functions like `__extends` in compiled output. */
|
||||
// "noEmitOnError": true, /* Disable emitting files if any type checking errors are reported. */
|
||||
// "preserveConstEnums": true, /* Disable erasing `const enum` declarations in generated code. */
|
||||
// "declarationDir": "./", /* Specify the output directory for generated declaration files. */
|
||||
// "preserveValueImports": true, /* Preserve unused imported values in the JavaScript output that would otherwise be removed. */
|
||||
|
||||
/* Interop Constraints */
|
||||
// "isolatedModules": true, /* Ensure that each file can be safely transpiled without relying on other imports. */
|
||||
// "allowSyntheticDefaultImports": true, /* Allow 'import x from y' when a module doesn't have a default export. */
|
||||
"esModuleInterop": true /* Emit additional JavaScript to ease support for importing CommonJS modules. This enables `allowSyntheticDefaultImports` for type compatibility. */,
|
||||
// "preserveSymlinks": true, /* Disable resolving symlinks to their realpath. This correlates to the same flag in node. */
|
||||
"forceConsistentCasingInFileNames": true /* Ensure that casing is correct in imports. */,
|
||||
|
||||
/* Type Checking */
|
||||
"strict": true /* Enable all strict type-checking options. */,
|
||||
"noImplicitAny": true, /* Enable error reporting for expressions and declarations with an implied `any` type.. */
|
||||
"strictNullChecks": true, /* When type checking, take into account `null` and `undefined`. */
|
||||
"strictFunctionTypes": true, /* When assigning functions, check to ensure parameters and the return values are subtype-compatible. */
|
||||
"strictBindCallApply": true, /* Check that the arguments for `bind`, `call`, and `apply` methods match the original function. */
|
||||
"strictPropertyInitialization": true, /* Check for class properties that are declared but not set in the constructor. */
|
||||
"noImplicitThis": true, /* Enable error reporting when `this` is given the type `any`. */
|
||||
"useUnknownInCatchVariables": true, /* Type catch clause variables as 'unknown' instead of 'any'. */
|
||||
"alwaysStrict": true, /* Ensure 'use strict' is always emitted. */
|
||||
"noUnusedLocals": true, /* Enable error reporting when a local variables aren't read. */
|
||||
"noUnusedParameters": true, /* Raise an error when a function parameter isn't read */
|
||||
"exactOptionalPropertyTypes": true, /* Interpret optional property types as written, rather than adding 'undefined'. */
|
||||
"noImplicitReturns": true, /* Enable error reporting for codepaths that do not explicitly return in a function. */
|
||||
"noFallthroughCasesInSwitch": true, /* Enable error reporting for fallthrough cases in switch statements. */
|
||||
"noUncheckedIndexedAccess": true, /* Include 'undefined' in index signature results */
|
||||
"noImplicitOverride": true, /* Ensure overriding members in derived classes are marked with an override modifier. */
|
||||
"noPropertyAccessFromIndexSignature": true, /* Enforces using indexed accessors for keys declared using an indexed type */
|
||||
// "allowUnusedLabels": true, /* Disable error reporting for unused labels. */
|
||||
// "allowUnreachableCode": true, /* Disable error reporting for unreachable code. */
|
||||
|
||||
/* Completeness */
|
||||
// "skipDefaultLibCheck": true, /* Skip type checking .d.ts files that are included with TypeScript. */
|
||||
"skipLibCheck": true, /* Skip type checking all .d.ts files. */
|
||||
"resolveJsonModule": true
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user