fork original

Dockerfile

@@ -0,0 +1,17 @@
+# Use an official Python runtime as the base image
+FROM amd64/python:3.9-buster as project_env
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install dependencies
+COPY requirements.txt requirements.txt
+RUN pip install --upgrade pip setuptools \
+    && pip install -r requirements.txt
+
+FROM project_env
+
+COPY . /app/
+
+# Set the entrypoint command
+CMD ["gunicorn", "--conf", "/app/gunicorn_conf.py", "main:app"]

config.py

@@ -0,0 +1,5 @@
+import os
+
+app_base_path = os.getenv("APP_BASE_PATH", default=os.getcwd())
+data_base_path = os.path.join(app_base_path, "data")
+model_file_path = os.path.join(data_base_path, "model.pkl")

gunicorn_conf.py

@@ -0,0 +1,12 @@
+# Gunicorn config variables
+loglevel = "info"
+errorlog = "-"  # stderr
+accesslog = "-"  # stdout
+worker_tmp_dir = "/dev/shm"
+graceful_timeout = 120
+timeout = 30
+keepalive = 5
+worker_class = "gthread"
+workers = 1
+threads = 8
+bind = "0.0.0.0:9000"

init.config

@@ -0,0 +1,43 @@
+#!/bin/bash
+
+set -e
+
+if [ ! -f config.json ]; then
+    echo "Error: config.json file not found, please provide one"
+    exit 1
+fi
+
+nodeName=$(jq -r '.wallet.addressKeyName' config.json)
+if [ -z "$nodeName" ]; then
+    echo "No wallet name provided for the node, please provide your preferred wallet name. config.json >> wallet.addressKeyName"
+    exit 1
+fi
+
+# Ensure the worker-data directory exists
+mkdir -p ./worker-data
+
+json_content=$(cat ./config.json)
+stringified_json=$(echo "$json_content" | jq -c .)
+
+mnemonic=$(jq -r '.wallet.addressRestoreMnemonic' config.json)
+if [ -n "$mnemonic" ]; then
+    echo "ALLORA_OFFCHAIN_NODE_CONFIG_JSON='$stringified_json'" > ./worker-data/env_file
+    echo "NAME=$nodeName" >> ./worker-data/env_file
+    echo "ENV_LOADED=true" >> ./worker-data/env_file
+    echo "wallet mnemonic already provided by you, loading config.json . Please proceed to run docker compose"
+    exit 1
+fi
+
+if [ ! -f ./worker-data/env_file ]; then
+    echo "ENV_LOADED=false" > ./worker-data/env_file
+fi
+
+ENV_LOADED=$(grep '^ENV_LOADED=' ./worker-data/env_file | cut -d '=' -f 2)
+if [ "$ENV_LOADED" = "false" ]; then
+    json_content=$(cat ./config.json)
+    stringified_json=$(echo "$json_content" | jq -c .)
+    docker run -it --entrypoint=bash -v $(pwd)/worker-data:/data -v $(pwd)/scripts:/scripts -e NAME="${nodeName}" -e ALLORA_OFFCHAIN_NODE_CONFIG_JSON="${stringified_json}" alloranetwork/allora-chain:latest -c "bash /scripts/init.sh"
+    echo "config.json saved to ./worker-data/env_file"
+else
+    echo "config.json is already loaded, skipping the operation. You can set ENV_LOADED variable to false in ./worker-data/env_file to reload the config.json"
+fi

requirements.txt

@@ -0,0 +1,7 @@
+flask[async]
+gunicorn[gthread]
+numpy==1.26.2
+pandas==2.1.3
+Requests==2.32.0
+scikit_learn==1.3.2
+werkzeug>=3.0.3 # not directly required, pinned by Snyk to avoid a vulnerability

scripts/init.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+
+set -e
+
+if allorad keys --home=/data/.allorad --keyring-backend test show $NAME > /dev/null 2>&1 ; then
+    echo "allora account: $NAME already imported"
+else
+    echo "creating allora account: $NAME"
+    output=$(allorad keys add $NAME --home=/data/.allorad --keyring-backend test 2>&1)
+    address=$(echo "$output" | grep 'address:' | sed 's/.*address: //')
+    mnemonic=$(echo "$output" | tail -n 1)
+    
+    # Parse and update the JSON string
+    updated_json=$(echo "$ALLORA_OFFCHAIN_NODE_CONFIG_JSON" | jq --arg name "$NAME" --arg mnemonic "$mnemonic" '
+    .wallet.addressKeyName = $name |
+    .wallet.addressRestoreMnemonic = $mnemonic
+    ')
+    
+    stringified_json=$(echo "$updated_json" | jq -c .)
+    
+    echo "ALLORA_OFFCHAIN_NODE_CONFIG_JSON='$stringified_json'" > /data/env_file
+    echo ALLORA_OFFCHAIN_ACCOUNT_ADDRESS=$address >> /data/env_file
+    echo "NAME=$NAME" >> /data/env_file
+    
+    echo "Updated ALLORA_OFFCHAIN_NODE_CONFIG_JSON saved to /data/env_file"
+fi
+
+
+if grep -q "ENV_LOADED=false" /data/env_file; then
+    sed -i 's/ENV_LOADED=false/ENV_LOADED=true/' /data/env_file
+else
+    echo "ENV_LOADED=true" >> /data/env_file
+fi

update_app.py

@@ -0,0 +1,22 @@
+import os
+import requests
+
+inference_address = os.environ["INFERENCE_API_ADDRESS"]
+url = f"{inference_address}/update"
+
+print("UPDATING INFERENCE WORKER DATA")
+
+response = requests.get(url)
+if response.status_code == 200:
+    # Request was successful
+    content = response.text
+
+    if content == "0":
+        print("Response content is '0'")
+        exit(0)
+    else:
+        exit(1)
+else:
+    # Request failed
+    print(f"Request failed with status code: {response.status_code}")
+    exit(1)

updater.py

@@ -0,0 +1,59 @@
+import os
+import requests
+from concurrent.futures import ThreadPoolExecutor
+
+
+# Function to download the URL, called asynchronously by several child processes
+def download_url(url, download_path):
+    target_file_path = os.path.join(download_path, os.path.basename(url)) 
+    if os.path.exists(target_file_path):
+        # print(f"File already exists: {url}")
+        return
+    
+    response = requests.get(url)
+    if response.status_code == 404:
+        # print(f"File not exist: {url}")
+        pass
+    else:
+
+        # create the entire path if it doesn't exist
+        os.makedirs(os.path.dirname(target_file_path), exist_ok=True)
+
+        with open(target_file_path, "wb") as f:
+            f.write(response.content)
+        # print(f"Downloaded: {url} to {target_file_path}")
+
+
+def download_binance_monthly_data(
+    cm_or_um, symbols, intervals, years, months, download_path
+):
+    # Verify if CM_OR_UM is correct, if not, exit
+    if cm_or_um not in ["cm", "um"]:
+        print("CM_OR_UM can be only cm or um")
+        return
+    base_url = f"https://data.binance.vision/data/futures/{cm_or_um}/monthly/klines"
+
+    # Main loop to iterate over all the arrays and launch child processes
+    with ThreadPoolExecutor() as executor:
+        for symbol in symbols:
+            for interval in intervals:
+                for year in years:
+                    for month in months:
+                        url = f"{base_url}/{symbol}/{interval}/{symbol}-{interval}-{year}-{month}.zip"
+                        executor.submit(download_url, url, download_path)
+
+
+def download_binance_daily_data(
+    cm_or_um, symbols, intervals, year, month, download_path
+):
+    if cm_or_um not in ["cm", "um"]:
+        print("CM_OR_UM can be only cm or um")
+        return
+    base_url = f"https://data.binance.vision/data/futures/{cm_or_um}/daily/klines"
+
+    with ThreadPoolExecutor() as executor:
+        for symbol in symbols:
+            for interval in intervals:
+                for day in range(1, 32):  # Assuming days range from 1 to 31
+                    url = f"{base_url}/{symbol}/{interval}/{symbol}-{interval}-{year}-{month:02d}-{day:02d}.zip"
+                    executor.submit(download_url, url, download_path)