Upload folder using huggingface_hub

README.md

@@ -5,7 +5,7 @@ emoji: 🔥
 colorFrom: indigo
 colorTo: indigo
 sdk: gradio
-sdk_version: 6.4.0
+sdk_version: 6.5.0
 app_file: run.py
 pinned: false
 hf_oauth: true

requirements.txt

@@ -1,2 +1,3 @@
 langchain
-langchain-openai
+langchain-openai
+pytz

run.ipynb

@@ -1 +1 @@
-{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: llm_langchain"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio langchain langchain-openai"]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["# This is a simple general-purpose chatbot built on top of LangChain and Gradio.\n", "# Before running this, make sure you have exported your OpenAI API key as an environment variable:\n", "# export OPENAI_API_KEY=\"your-openai-api-key\"\n", "\n", "from langchain_openai import ChatOpenAI  # type: ignore\n", "from langchain.schema import AIMessage, HumanMessage  # type: ignore\n", "import gradio as gr\n", "\n", "model = ChatOpenAI(model=\"gpt-4o-mini\")\n", "\n", "def predict(message, history):\n", "    history_langchain_format = []\n", "    for msg in history:\n", "        if msg['role'] == \"user\":\n", "            history_langchain_format.append(HumanMessage(content=msg['content']))\n", "        elif msg['role'] == \"assistant\":\n", "            history_langchain_format.append(AIMessage(content=msg['content']))\n", "    history_langchain_format.append(HumanMessage(content=message))\n", "    gpt_response = model.invoke(history_langchain_format)\n", "    return gpt_response.content\n", "\n", "demo = gr.ChatInterface(\n", "    predict,\n", "    api_name=\"chat\",\n", ")\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}
+{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: llm_langchain"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio langchain langchain-openai pytz "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["# This is a simple general-purpose chatbot built on top of LangChain and Gradio.\n", "# Before running this, make sure you have exported your OpenAI API key as an environment variable:\n", "# export OPENAI_API_KEY=\"your-openai-api-key\"\n", "\n", "import gradio as gr\n", "from langchain.messages import AIMessage, HumanMessage  # type: ignore\n", "from langchain_openai import ChatOpenAI  # type: ignore\n", "\n", "model = ChatOpenAI(model=\"gpt-4o-mini\")\n", "\n", "\n", "def predict(message, history):\n", "    history_langchain_format = []\n", "    for msg in history:\n", "        if msg[\"role\"] == \"user\":\n", "            history_langchain_format.append(HumanMessage(content=msg[\"content\"]))\n", "        elif msg[\"role\"] == \"assistant\":\n", "            history_langchain_format.append(AIMessage(content=msg[\"content\"]))\n", "    history_langchain_format.append(HumanMessage(content=message))\n", "    gpt_response = model.invoke(history_langchain_format)\n", "    return gpt_response.content\n", "\n", "\n", "demo = gr.ChatInterface(\n", "    predict,\n", "    api_name=\"chat\",\n", ")\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}

run.py

@@ -2,23 +2,25 @@
 # Before running this, make sure you have exported your OpenAI API key as an environment variable:
 # export OPENAI_API_KEY="your-openai-api-key"
 
-from langchain_openai import ChatOpenAI  # type: ignore
-from langchain.schema import AIMessage, HumanMessage  # type: ignore
 import gradio as gr
+from langchain.messages import AIMessage, HumanMessage  # type: ignore
+from langchain_openai import ChatOpenAI  # type: ignore
 
 model = ChatOpenAI(model="gpt-4o-mini")
 
+
 def predict(message, history):
     history_langchain_format = []
     for msg in history:
-        if msg['role'] == "user":
-            history_langchain_format.append(HumanMessage(content=msg['content']))
-        elif msg['role'] == "assistant":
-            history_langchain_format.append(AIMessage(content=msg['content']))
+        if msg["role"] == "user":
+            history_langchain_format.append(HumanMessage(content=msg["content"]))
+        elif msg["role"] == "assistant":
+            history_langchain_format.append(AIMessage(content=msg["content"]))
     history_langchain_format.append(HumanMessage(content=message))
     gpt_response = model.invoke(history_langchain_format)
     return gpt_response.content
 
+
 demo = gr.ChatInterface(
     predict,
     api_name="chat",