Upload 7 files

README.md

@@ -1,13 +1,17 @@
 ---
-title: KhangeyAI
-emoji: 👁
-colorFrom: blue
-colorTo: green
+title: Chatbot Tibetan
+emoji: 🤖
+colorFrom: green
+colorTo: purple
 sdk: gradio
-sdk_version: 4.1.1
+sdk_version: 3.26.0
 app_file: app.py
 pinned: false
-license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<iframe
+	src="https://openpecha-chatbot-tibetan.hf.space"
+	frameborder="0"
+	width="850"
+	height="450"
+></iframe>

chat.py

@@ -0,0 +1,66 @@
+import os
+from typing import Tuple
+
+import openai
+
+
+class ChatGpt:
+    def __init__(self, api_key, max_tokens=4096):
+        self.api_key = api_key
+        self.max_tokens = max_tokens
+        self.message_history = []
+        self.total_tokens = 0
+
+        # Set up the OpenAI API client
+        openai.api_key = self.api_key
+
+    def clear_history(self):
+        self.message_history = []
+        self.total_tokens = 0
+
+    def add_message(self, role: str, content: str):
+        self.message_history.append({"role": role, "content": content})
+        self._truncate_history()
+
+    def add_system_message(self, content: str):
+        self.add_message("system", content)
+
+    def generate_response(self, user_input: str) -> str:
+        self.add_message("user", user_input)
+        response = self._call_openai_api(self.message_history)
+        self.add_message("assistant", response)
+
+        return response
+
+    def _truncate_history(self):
+        while self.total_tokens > self.max_tokens:
+            if self.message_history[0]["role"] != "system":
+                self.message_history.pop(0)
+            else:
+                break
+
+    def _call_openai_api(self, messages) -> str:
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo", messages=messages
+        )
+        self.total_tokens += response["usage"]["total_tokens"]
+        return response["choices"][0]["message"]["content"].strip()
+
+
+if __name__ == "__main__":
+    chat = ChatGpt(os.getenv("OPENAI_API_KEY"))
+
+    chat.add_system_message("The assistant can answer questions and tell jokes.")
+    user_input = "Tell me a joke."
+    user_msg, bot_response = chat.generate_response(user_input)
+    assert user_msg == user_input
+    print("User:", user_msg)
+    print("Assistant:", bot_response)
+    print("Total Tokens:", chat.total_tokens)
+
+    user_input = "another one"
+    user_msg, bot_response = chat.generate_response(user_input)
+    assert user_msg == user_input
+    print("User:", user_msg)
+    print("Assistant:", bot_response)
+    print("Total Tokens:", chat.total_tokens)

gitattributes.txt

@@ -0,0 +1,34 @@
+*.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
+*.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.txt

@@ -0,0 +1,163 @@
+# 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/
+
+.vscode
+prompts.py

requirements.txt

@@ -0,0 +1,4 @@
+gradio==3.26.0
+requests==2.28.2
+boto3==1.26.113
+openai==0.27.4, <1.0

static/app.css

@@ -0,0 +1,17 @@
+#maiChatHistory .message-wrap div {
+    font-size: 30px;
+}
+
+#maiChatInput textarea {
+    font-size: 30px
+}
+
+@media screen and (min-width: 768px) {
+    #maiChatInput textarea {
+        font-size: 20px
+    }
+
+    #maiChatHistory .message-wrap div {
+        font-size: 20px;
+    }
+}

store.py

@@ -0,0 +1,42 @@
+import json
+import uuid
+from datetime import datetime
+from typing import Dict, Tuple
+
+import boto3
+
+dynamodb = boto3.resource("dynamodb", region_name="us-east-1")
+all_chats_table = dynamodb.Table("ChatbotTibetanAllChats")
+
+
+def store_message_pair(chat_id: str, msg_pair: Dict[str, Tuple[str, str]]):
+    """Store the chat history to DynamoDB
+
+    Args:
+        chat_id: The ID of the chat
+        msg_pair: tuple with 2 items (user_message, bot_response)
+        lang: The language of the msg_pair
+        order: The order of the msg_pair in chat history
+    """
+
+    # Add the new message to the chat history
+    msg_pair_id = uuid.uuid4().hex[:10]
+    response = all_chats_table.put_item(
+        Item={
+            "msg_pair_id": msg_pair_id,
+            "msg_pair": json.dumps(msg_pair, ensure_ascii=False),
+            "created_at": datetime.now().isoformat(),
+            "chat_id": chat_id,
+        }
+    )
+    return response
+
+
+if __name__ == "__main__":
+    # Replace with your own DynamoDB table name and chat ID
+    chat_id = str(uuid.uuid4())
+
+    # Replace with your own chat history (list of tuples or list of dictionaries)
+    msg_pair = {"bo": ("hello", "hello"), "en": ("hello", "hello")}
+    response = store_message_pair(chat_id, msg_pair)
+    print(response)