Duplicate from PawinC/Alpaca-Flask

.env

@@ -0,0 +1,2 @@
+debugModeEnabled="True"
+port="7860"

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,179 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+Playground.ipynb
+archive/
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python

Dockerfile

@@ -0,0 +1,23 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD ["python", "main.py"]

README.md

@@ -0,0 +1,11 @@
+---
+title: Alpaca Flask
+emoji: 🦙
+colorFrom: purple
+colorTo: indigo
+sdk: docker
+pinned: false
+duplicated_from: PawinC/Alpaca-Flask
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

client.py

@@ -0,0 +1,30 @@
+import time, requests
+
+serverIsPreparing = True
+print("Checking server status")
+while serverIsPreparing:
+  try:
+    with requests.get("http://localhost:8080/chat") as r:
+      print("Status Check: " + r.text)
+      if r.text == 'Ready':
+        break
+      else:
+        time.sleep(5)
+  except requests.exceptions.ConnectionError:
+    print("Connection Refused. Retrying in 5 seconds.")
+    time.sleep(5)
+
+print("Server is ready. Starting client.")
+headers = {"Content-type": "application/json", "Authorization": "test:test"}
+messages = [
+  {"role": "user", "content": "Hello, how are you feeling today?"},
+  {"role": "assistant", "content": "I'm feeling great. How about you?"},
+  {"role": "user", "content": "I'm fine, thanks for asking."}
+  ]
+
+print("Sending Request...")
+try:
+  with requests.post("http://localhost:8080/chat", headers=headers, json=messages) as r:
+    print(r.json()["content"])
+except requests.exceptions.JSONDecodeError:
+  print(f"Something went wrong: {r.status_code}- {r.text}")

dockerfile

@@ -0,0 +1,23 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD ["python", "main.py"]

main.py

@@ -0,0 +1,122 @@
+from flask import Flask, render_template, request, abort, redirect, url_for, Response
+from werkzeug.security import generate_password_hash, check_password_hash
+from werkzeug.exceptions import HTTPException
+
+import os, threading, json, waitress, datetime
+from llama_cpp import Llama
+from dotenv import load_dotenv
+load_dotenv()
+
+#Variables
+DEBUGMODEENABLED = (os.getenv('debugModeEnabled', 'False') == 'True')
+llm = None
+AlpacaLoaded = False
+
+#Chat Functions
+def load_alpaca():
+  global llm, AlpacaLoaded
+  if not AlpacaLoaded:
+    print("Loading Alpaca...")
+    try:
+      llm = Llama(model_path="./resources/ggml-model-q4_0.bin", use_mmap=False, n_threads=2, verbose=False) #use_mlock=True
+      AlpacaLoaded = True
+      print("Done loading Alpaca.")
+    except AttributeError:
+      print("Error loading Alpaca. Please make sure you have the model file in the resources folder.")
+  else:
+    print("Alpaca already loaded.")
+
+def getChatResponse(modelOutput):
+  return str(modelOutput["choices"][0]['message']['content'])
+
+
+#Authentication Functions
+def loadHashes():
+  global hashesDict
+  try:
+    with open("resources/hashes.json", "r") as f:
+      hashesDict = json.load(f)
+  except FileNotFoundError:
+    hashesDict = {}
+  
+def saveHashes():
+  global hashesDict
+  with open("resources/hashes.json", "w") as f:
+    json.dump(hashesDict, f)
+
+def addHashes(username: str, password: str):
+  global hashesDict
+  hashesDict[username] = generate_password_hash(password, method='scrypt')
+  saveHashes()
+
+def checkCredentials(username: str , password: str):
+  global hashesDict
+  if username in hashesDict:
+    return check_password_hash(hashesDict[username], password)
+  else:
+    return False
+
+def verifyHeaders():
+  #Check + Obtain Authorization header
+  try:
+    user, passw = request.headers['Authorization'].split(":")
+  except (KeyError, ValueError):
+    abort(401)
+
+  #Check if Authorization header is valid
+  credentialsValid = checkCredentials(user, passw)
+  if not credentialsValid:
+    abort(403)
+  else:
+    return user
+
+
+loadHashes()
+#addHashes("test", "test")
+
+#General Functions
+def getIsoTime():
+  return str(datetime.datetime.now().isoformat())
+
+#Flask App
+app = Flask(__name__)
+
+@app.route('/')
+def main():
+  return """<!DOCTYPE HTML>
+<html>
+  <head><meta name='color-scheme' content='dark'></head>
+  <body><p>Hello, World!</p></body>
+</html>"""
+
+@app.route('/chat', methods=['GET', 'POST'])
+def chat():
+  if request.method == 'POST':
+    verifyHeaders()
+    print("Headers verified")
+    messages = request.get_json()
+    print("Got Message" + str(messages))
+
+    if AlpacaLoaded:
+      modelOutput = llm.create_chat_completion(messages=messages, max_tokens=128)
+      responseMessage = modelOutput["choices"][0]['message']
+      print(f"\n\nResponseMessage: {responseMessage}\n\n")
+      return Response(json.dumps(responseMessage, indent=2), content_type='application/json')
+    else:
+      abort(503, "Alpaca not loaded. Please wait a few seconds and try again.")
+  else:
+    return "Ready" if AlpacaLoaded else "Not Ready", 200 if AlpacaLoaded else 503
+
+@app.errorhandler(HTTPException)
+def handle_exception(e):
+  return Response({"error": f"{e.code} - {e.name}", "message": e.description}, content_type='application/json'), e.code
+
+if __name__ == '__main__':
+  t = threading.Thread(target=load_alpaca, daemon=True).start()
+
+  port = int(os.getenv("port", "8080"))
+  print("Server successfully started.")
+  if DEBUGMODEENABLED:
+    app.run(host='0.0.0.0', port=port)
+  else:
+    waitress.serve(app, host='0.0.0.0', port=port, url_scheme='https')

requirements.txt

@@ -0,0 +1,4 @@
+flask
+waitress
+llama-cpp-python
+python-dotenv

resources/ggml-model-q4_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d3f6cea80442f3c30e576540c95dc6d516c20e2002446ff278853a4cefdee9
+size 3791729792

resources/hashes.json

@@ -0,0 +1 @@
+{"test": "scrypt:32768:8:1$HBHtLz3s0Q8bmGFk$0af12bbd68d1b12498d64fc4508ccd848f183fbcfda1f0771788323776bbeeaa69316299228b8aa182f6601cab3c68567116ca5b2970a69538a331897510fef7"}