mirror of
https://github.com/hwchase17/langchain.git
synced 2026-07-13 12:14:06 +00:00
docs: add Qwen integration guide and update qwq documentation (#32817)
Thank you for contributing to LangChain! Follow these steps to mark your pull request as ready for review. **If any of these steps are not completed, your PR will not be considered for review.** **Description:** Add documentation for Qwen integration in LangChain, including setup instructions, usage examples, and configuration details. Update related qwq documentation to reflect current best practices and improve clarity for users. This PR enhances the documentation ecosystem by: - Adding a new guide for integrating Qwen models - Updating outdated or incomplete qwq documentation - Improving structure and readability of relevant sections **Issue:** N/A **Dependencies:** None --------- Co-authored-by: Mason Daugherty <mason@langchain.dev>
This commit is contained in:
tbice
GitHub
408
docs/docs/integrations/chat/qwen.ipynb
Normal file
408
docs/docs/integrations/chat/qwen.ipynb
Normal file
@@ -0,0 +1,408 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "afaf8039",
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "raw"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_label: Qwen\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e49f1e0d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ChatQwen\n",
|
||||
"\n",
|
||||
"This will help you get started with Qwen [chat models](../../concepts/chat_models.mdx). For detailed documentation of all ChatQwen features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/).\n",
|
||||
"\n",
|
||||
"## Overview\n",
|
||||
"### Integration details\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"| Class | Package | Local | Serializable | Package downloads | Package latest |\n",
|
||||
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
|
||||
"| [ChatQwen](https://pypi.org/project/langchain-qwq/) | [langchain-qwq](https://pypi.org/project/langchain-qwq/) | ❌ | beta |  |  |\n",
|
||||
"\n",
|
||||
"### Model features\n",
|
||||
"| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
|
||||
"| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |\n",
|
||||
"| ✅ | ✅ | ✅ |✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | \n",
|
||||
"\n",
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"To access Qwen models you'll need to create an Alibaba Cloud account, get an API key, and install the `langchain-qwq` integration package.\n",
|
||||
"\n",
|
||||
"### Credentials\n",
|
||||
"\n",
|
||||
"Head to [Alibaba's API Key page](https://account.alibabacloud.com/login/login.htm?oauth_callback=https%3A%2F%2Fbailian.console.alibabacloud.com%2F%3FapiKey%3D1&lang=en#/api-key) to sign up to Alibaba Cloud and generate an API key. Once you've done this set the `DASHSCOPE_API_KEY` environment variable:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import getpass\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"if not os.getenv(\"DASHSCOPE_API_KEY\"):\n",
|
||||
" os.environ[\"DASHSCOPE_API_KEY\"] = getpass.getpass(\"Enter your Dashscope API key: \")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0730d6a1-c893-4840-9817-5e5251676d5d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Installation\n",
|
||||
"\n",
|
||||
"The LangChain QwQ integration lives in the `langchain-qwq` package:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "652d6238-1f87-422a-b135-f5abbb8652fc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install -qU langchain-qwq"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a38cde65-254d-4219-a441-068766c0d4b5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Instantiation\n",
|
||||
"\n",
|
||||
"Now we can instantiate our model object and generate chat completions:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Hello! How can I assist you today? 😊', additional_kwargs={}, response_metadata={'finish_reason': 'stop', 'model_name': 'qwen-flash'}, id='run--62798a20-d425-48ab-91fc-8e62e37c6084-0', usage_metadata={'input_tokens': 9, 'output_tokens': 11, 'total_tokens': 20, 'input_token_details': {}, 'output_token_details': {}})"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_qwq import ChatQwen\n",
|
||||
"\n",
|
||||
"llm = ChatQwen(model=\"qwen-flash\")\n",
|
||||
"response = llm.invoke(\"Hello\")\n",
|
||||
"\n",
|
||||
"response"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2b4f3e15",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Invocation"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "62e0dbc3",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content=\"J'adore la programmation.\", additional_kwargs={}, response_metadata={'finish_reason': 'stop', 'model_name': 'qwen-flash'}, id='run--33f905e0-880a-4a67-ab83-313fd7a06369-0', usage_metadata={'input_tokens': 32, 'output_tokens': 8, 'total_tokens': 40, 'input_token_details': {}, 'output_token_details': {}})"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"messages = [\n",
|
||||
" (\n",
|
||||
" \"system\",\n",
|
||||
" \"You are a helpful assistant that translates English to French.\"\n",
|
||||
" \"Translate the user sentence.\",\n",
|
||||
" ),\n",
|
||||
" (\"human\", \"I love programming.\"),\n",
|
||||
"]\n",
|
||||
"ai_msg = llm.invoke(messages)\n",
|
||||
"ai_msg"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Chaining\n",
|
||||
"\n",
|
||||
"We can [chain](../../how_to/sequence.ipynb) our model with a prompt template like so:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Ich liebe Programmierung.', additional_kwargs={}, response_metadata={'finish_reason': 'stop', 'model_name': 'qwen-flash'}, id='run--9d8bab6d-d6fe-4b9f-95f2-c30c3ff0a50e-0', usage_metadata={'input_tokens': 28, 'output_tokens': 5, 'total_tokens': 33, 'input_token_details': {}, 'output_token_details': {}})"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.prompts import ChatPromptTemplate\n",
|
||||
"\n",
|
||||
"prompt = ChatPromptTemplate(\n",
|
||||
" [\n",
|
||||
" (\n",
|
||||
" \"system\",\n",
|
||||
" \"You are a helpful assistant that translates\"\n",
|
||||
" \"{input_language} to {output_language}.\",\n",
|
||||
" ),\n",
|
||||
" (\"human\", \"{input}\"),\n",
|
||||
" ]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"chain = prompt | llm\n",
|
||||
"chain.invoke(\n",
|
||||
" {\n",
|
||||
" \"input_language\": \"English\",\n",
|
||||
" \"output_language\": \"German\",\n",
|
||||
" \"input\": \"I love programming.\",\n",
|
||||
" }\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "8d1b3ef3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Tool Calling\n",
|
||||
"ChatQwen supports tool calling API that lets you describe tools and their arguments, and have the model return a JSON object with a tool to invoke and the inputs to that tool."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6db1a355",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Use with `bind_tools`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "15fb6a6d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"content='' additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_f0c2cc49307f480db78a45', 'function': {'arguments': '{\"first_int\": 5, \"second_int\": 42}', 'name': 'multiply'}, 'type': 'function'}]} response_metadata={'finish_reason': 'tool_calls', 'model_name': 'qwen-flash'} id='run--27c5aafb-9710-42f5-ab78-5a2ad1d9050e-0' tool_calls=[{'name': 'multiply', 'args': {'first_int': 5, 'second_int': 42}, 'id': 'call_f0c2cc49307f480db78a45', 'type': 'tool_call'}] usage_metadata={'input_tokens': 166, 'output_tokens': 27, 'total_tokens': 193, 'input_token_details': {}, 'output_token_details': {}}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.tools import tool\n",
|
||||
"\n",
|
||||
"from langchain_qwq import ChatQwen\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"@tool\n",
|
||||
"def multiply(first_int: int, second_int: int) -> int:\n",
|
||||
" \"\"\"Multiply two integers together.\"\"\"\n",
|
||||
" return first_int * second_int\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"llm = ChatQwen(model=\"qwen-flash\")\n",
|
||||
"\n",
|
||||
"llm_with_tools = llm.bind_tools([multiply])\n",
|
||||
"\n",
|
||||
"msg = llm_with_tools.invoke(\"What's 5 times forty two\")\n",
|
||||
"\n",
|
||||
"print(msg)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "cc8ffd89-c474-45a7-a123-e0b1d362f54f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### vision Support"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3e8a7d46-d1f6-4ae8-835a-266ca47e4daf",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "54f69db3-fa51-4b9a-885c-1353968066e3",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"This image depicts a cozy, rustic Christmas scene set against a wooden backdrop. The arrangement features a variety of festive decorations that evoke a warm, holiday atmosphere:\n",
|
||||
"\n",
|
||||
"- **Centerpiece**: A decorative reindeer figurine with large antlers stands prominently in the background.\n",
|
||||
"- **Miniature Trees**: Two small, snow-dusted artificial Christmas trees flank the reindeer, adding to the wintry feel.\n",
|
||||
"- **Candles**: Three log-shaped candle holders made from birch bark are lit, casting a soft, warm glow. Two are in the foreground, and one is slightly behind them.\n",
|
||||
"- **\"Merry Christmas\" Sign**: A wooden cutout sign spelling \"MERRY CHRISTMAS\" is placed on the left, decorated with a tiny golden gift box and a small reindeer silhouette.\n",
|
||||
"- **Holiday Elements**: Pinecones, red berries, greenery, and fairy lights are scattered throughout, enhancing the natural, festive theme.\n",
|
||||
"- **Other Details**: A white sack with \"SANTA\" written on it is partially visible on the left, along with a large glass ornament and twinkling string lights.\n",
|
||||
"\n",
|
||||
"The overall aesthetic is warm, inviting, and traditional, emphasizing natural materials like wood, pine, and birch bark. It captures the essence of a rustic, homemade Christmas celebration.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.messages import HumanMessage\n",
|
||||
"\n",
|
||||
"model = ChatQwen(model=\"qwen-vl-max-latest\")\n",
|
||||
"\n",
|
||||
"messages = [\n",
|
||||
" HumanMessage(\n",
|
||||
" content=[\n",
|
||||
" {\n",
|
||||
" \"type\": \"image_url\",\n",
|
||||
" \"image_url\": {\"url\": \"https://example.com/image/image.png\"},\n",
|
||||
" },\n",
|
||||
" {\"type\": \"text\", \"text\": \"What do you see in this image?\"},\n",
|
||||
" ]\n",
|
||||
" )\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"response = model.invoke(messages)\n",
|
||||
"print(response.content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b1faea19-932f-4dc8-b0af-60e3507eee08",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Video"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "59355c38-d3e2-4051-811a-2b99286ea01b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"This video features a young woman with a warm and cheerful expression, standing outdoors in a well-lit environment. She has short, neatly styled brown hair with bangs and is wearing a soft pink knitted cardigan over a white top. A delicate necklace adorns her neck, adding a subtle touch of elegance to her outfit.\n",
|
||||
"\n",
|
||||
"Throughout the video, she maintains eye contact with the camera, smiling gently and occasionally opening her mouth as if speaking or laughing. Her facial expressions are natural and engaging, suggesting a friendly and approachable demeanor. The background is softly blurred, indicating a shallow depth of field, which keeps the focus on her. It appears to be an urban setting with modern buildings, possibly a residential or commercial area.\n",
|
||||
"\n",
|
||||
"The lighting is bright and natural, likely from sunlight, casting a soft glow on her face and highlighting her features. The overall tone of the video is pleasant and inviting, evoking a sense of warmth and positivity.\n",
|
||||
"\n",
|
||||
"In the top right corner of the frames, there is a watermark that reads \"通义·AI合成,\" which indicates that this video was generated using AI technology by Tongyi Lab, a company known for its advancements in artificial intelligence and digital content creation. This suggests that the video may be a demonstration of AI-generated human-like avatars or synthetic media.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.messages import HumanMessage\n",
|
||||
"\n",
|
||||
"model = ChatQwen(model=\"qwen-vl-max-latest\")\n",
|
||||
"\n",
|
||||
"messages = [\n",
|
||||
" HumanMessage(\n",
|
||||
" content=[\n",
|
||||
" {\n",
|
||||
" \"type\": \"video_url\",\n",
|
||||
" \"video_url\": {\"url\": \"https://example.com/video/1.mp4\"},\n",
|
||||
" },\n",
|
||||
" {\"type\": \"text\", \"text\": \"Can you tell me about this video?\"},\n",
|
||||
" ]\n",
|
||||
" )\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"response = model.invoke(messages)\n",
|
||||
"print(response.content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## API reference\n",
|
||||
"\n",
|
||||
"For detailed documentation of all ChatQwen features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ce1026e3",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -34,7 +34,7 @@
|
||||
"### Model features\n",
|
||||
"| [Tool calling](../../how_to/tool_calling.ipynb) | [Structured output](../../how_to/structured_output.ipynb) | JSON mode | [Image input](../../how_to/multimodal_inputs.ipynb) | Audio input | Video input | [Token-level streaming](../../how_to/chat_streaming.ipynb) | Native async | [Token usage](../../how_to/chat_token_usage_tracking.ipynb) | [Logprobs](../../how_to/logprobs.ipynb) |\n",
|
||||
"| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |\n",
|
||||
"| ✅ | ✅ | ✅ |❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | \n",
|
||||
"| ✅ | ✅ | ✅ |✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | \n",
|
||||
"\n",
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
@@ -47,7 +47,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 1,
|
||||
"id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -91,7 +91,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 2,
|
||||
"id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -117,7 +117,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 3,
|
||||
"id": "62e0dbc3",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
@@ -126,10 +126,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content=\"J'aime la programmation.\", additional_kwargs={'reasoning_content': 'Okay, the user wants me to translate \"I love programming.\" into French. Let\\'s start by breaking down the sentence. The subject is \"I\", which in French is \"Je\". The verb is \"love\", which in this context is present tense, so \"aime\". The object is \"programming\". Now, \"programming\" in French can be \"la programmation\". \\n\\nWait, should it be \"programmation\" or \"programmation\"? Let me confirm the spelling. Yes, \"programmation\" is correct. Now, putting it all together: \"Je aime la programmation.\" Hmm, but in French, there\\'s a tendency to contract \"je\" and \"aime\". Wait, actually, \"je\" followed by a vowel sound usually takes \"j\\'\". So it should be \"J\\'aime la programmation.\" \\n\\nLet me double-check. \"J\\'aime\" is the correct contraction for \"I love\". The definite article \"la\" is needed because \"programmation\" is a feminine noun. Yes, \"programmation\" is a feminine noun, so \"la\" is correct. \\n\\nIs there any other way to say it? Maybe \"J\\'adore la programmation\" for \"I love\" in a stronger sense, but the user didn\\'t specify the intensity. Since the original is straightforward, \"J\\'aime la programmation.\" is the direct translation. \\n\\nI think that\\'s it. No mistakes there. So the final translation should be \"J\\'aime la programmation.\"'}, response_metadata={'model_name': 'qwq-plus'}, id='run-5045cd6a-edbd-4b2f-bf24-b7bdf3777fb9-0', usage_metadata={'input_tokens': 32, 'output_tokens': 326, 'total_tokens': 358, 'input_token_details': {}, 'output_token_details': {}})"
|
||||
"AIMessage(content=\"J'aime la programmation.\", additional_kwargs={'reasoning_content': 'Okay, the user wants me to translate \"I love programming.\" into French. Let me start by recalling the basic translation. The verb \"love\" in French is \"aimer\", and \"programming\" is \"la programmation\". So the literal translation would be \"J\\'aime la programmation.\" But wait, I should check if there\\'s any context or nuances I need to consider. The user mentioned they\\'re a helpful assistant, so maybe they want a more natural or commonly used phrase. Sometimes in French, people might use \"adorer\" instead of \"aimer\" for stronger emphasis, but \"aimer\" is more standard here. Also, the structure \"J\\'aime\" is correct for \"I love\". No need for any articles if it\\'s a general statement, but \"la programmation\" is a feminine noun, so the article is necessary. Let me confirm the gender of \"programmation\"—yes, it\\'s feminine. So \"la\" is correct. I think that\\'s it. The translation should be \"J\\'aime la programmation.\"'}, response_metadata={'model_name': 'qwq-plus'}, id='run--396edf0f-ab92-4317-99be-cc9f5377c312-0', usage_metadata={'input_tokens': 32, 'output_tokens': 229, 'total_tokens': 261, 'input_token_details': {}, 'output_token_details': {}})"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -159,17 +159,17 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 4,
|
||||
"id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Ich liebe das Programmieren.', additional_kwargs={'reasoning_content': 'Okay, the user wants me to translate \"I love programming.\" into German. Let me think. The verb \"love\" is \"lieben\" or \"mögen\" in German, but \"lieben\" is more like love, while \"mögen\" is prefer. Since it\\'s about programming, which is a strong affection, \"lieben\" is better. The subject is \"I\", which is \"ich\". Then \"programming\" is \"Programmierung\" or \"Coding\". But \"Programmierung\" is more formal. Alternatively, sometimes people say \"ich liebe es zu programmieren\" which is \"I love to program\". Hmm, maybe the direct translation would be \"Ich liebe die Programmierung.\" But maybe the more natural way is \"Ich liebe es zu programmieren.\" Let me check. Both are correct, but the second one might sound more natural in everyday speech. The user might prefer the concise version. Alternatively, maybe \"Ich liebe die Programmierung.\" is better. Wait, the original is \"programming\" as a noun. So using the noun form would be appropriate. So \"Ich liebe die Programmierung.\" But sometimes people also use \"Coding\" in German, like \"Ich liebe das Coding.\" But that\\'s more anglicism. Probably better to stick with \"Programmierung\". Alternatively, \"Programmieren\" as a noun. Oh right! \"Programmieren\" can be a noun when used in the accusative case. So \"Ich liebe das Programmieren.\" That\\'s correct and natural. Yes, that\\'s the best translation. So the answer is \"Ich liebe das Programmieren.\"'}, response_metadata={'model_name': 'qwq-plus'}, id='run-2c418451-51d8-4319-8269-2ce129363a1a-0', usage_metadata={'input_tokens': 28, 'output_tokens': 341, 'total_tokens': 369, 'input_token_details': {}, 'output_token_details': {}})"
|
||||
"AIMessage(content='Ich liebe das Programmieren.', additional_kwargs={'reasoning_content': 'Okay, the user wants to translate \"I love programming.\" into German. Let\\'s start by breaking down the sentence. The subject is \"I,\" which translates to \"Ich\" in German. The verb \"love\" is \"liebe\" in present tense for the first person singular. Then \"programming\" is a noun. Now, in German, the word for programming, especially in the context of computer programming, is \"Programmierung.\" However, sometimes people might use \"Programmieren\" as well. Wait, but \"Programmierung\" is the noun form, so \"die Programmierung.\" The structure in German would be \"Ich liebe die Programmierung.\" Alternatively, could it be \"Programmieren\" as the verb in a nominalized form? Let me think. If you say \"Ich liebe das Programmieren,\" that\\'s also correct because \"das Programmieren\" is the gerundive form, which is commonly used for activities. So both are possible. Which one is more natural? Hmm. \"Das Programmieren\" might be more common in everyday language. Let me check some examples. For instance, \"I love cooking\" would be \"Ich liebe das Kochen.\" So following that pattern, \"Ich liebe das Programmieren\" would be the equivalent. Therefore, maybe \"Programmieren\" with the article \"das\" is better here. But the user might just want a direct translation without the article. Wait, the original sentence is \"I love programming,\" which is a noun, so in German, you need an article. So the correct translation would include \"das\" before the noun. So the correct sentence is \"Ich liebe das Programmieren.\" Alternatively, if they want to use the noun without an article, maybe in a more abstract sense, but I think \"das\" is necessary here. Let me confirm. Yes, in German, when using the noun form of a verb like this, you need the article. So the best translation is \"Ich liebe das Programmieren.\" I think that\\'s the most natural way to say it. Alternatively, \"Programmierung\" is more formal, but \"Programmieren\" is more commonly used in such contexts. So I\\'ll go with \"Ich liebe das Programmieren.\"'}, response_metadata={'model_name': 'qwq-plus'}, id='run--0ceaba8a-7842-48fb-8bec-eb96d2c83ed4-0', usage_metadata={'input_tokens': 28, 'output_tokens': 466, 'total_tokens': 494, 'input_token_details': {}, 'output_token_details': {}})"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -217,7 +217,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 5,
|
||||
"id": "15fb6a6d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -225,12 +225,13 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"content='' additional_kwargs={'reasoning_content': 'Okay, the user is asking \"What\\'s 5 times forty two\". Let me break this down. First, I need to identify the numbers involved. The first number is 5, which is straightforward. The second number is forty two, which is 42 in digits. The operation they want is multiplication.\\n\\nLooking at the tools provided, there\\'s a function called multiply that takes two integers. So I should use that. The parameters are first_int and second_int. \\n\\nI need to convert \"forty two\" to 42. Since the function requires integers, both numbers should be in integer form. So 5 and 42. \\n\\nNow, I\\'ll structure the tool call. The function name is multiply, and the arguments should be first_int: 5 and second_int: 42. I\\'ll make sure the JSON is correctly formatted without any syntax errors. Let me double-check the parameters to ensure they\\'re required and of the right type. Yep, both are required and integers. \\n\\nNo examples were provided, but the function\\'s purpose is clear. So the correct tool call should be to multiply those two numbers. I think that\\'s all. No other functions are needed here.'} response_metadata={'model_name': 'qwq-plus'} id='run-638895aa-fdde-4567-bcfa-7d8e5d4f24af-0' tool_calls=[{'name': 'multiply', 'args': {'first_int': 5, 'second_int': 42}, 'id': 'call_d088275851c140529ed2ad', 'type': 'tool_call'}] usage_metadata={'input_tokens': 176, 'output_tokens': 277, 'total_tokens': 453, 'input_token_details': {}, 'output_token_details': {}}\n"
|
||||
"content='' additional_kwargs={'reasoning_content': 'Okay, the user is asking \"What\\'s 5 times forty two\". Let me break this down. They want the product of 5 and 42. The function provided is called multiply, which takes two integers. First, I need to parse the numbers from the question. The first integer is 5, straightforward. The second is forty two, which is 42 in numeric form. So I should call the multiply function with first_int=5 and second_int=42. Let me double-check the parameters: both are required and of type integer. Yep, that\\'s correct. No examples given, but the function should handle these numbers. Alright, time to format the tool call.'} response_metadata={'model_name': 'qwq-plus'} id='run--3c5ff46c-3fc8-4caf-a665-2405aeef2948-0' tool_calls=[{'name': 'multiply', 'args': {'first_int': 5, 'second_int': 42}, 'id': 'call_33fb94c6662d44928e56ec', 'type': 'tool_call'}] usage_metadata={'input_tokens': 176, 'output_tokens': 173, 'total_tokens': 349, 'input_token_details': {}, 'output_token_details': {}}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.tools import tool\n",
|
||||
"\n",
|
||||
"from langchain_qwq import ChatQwQ\n",
|
||||
"\n",
|
||||
"\n",
|
||||
@@ -249,6 +250,170 @@
|
||||
"print(msg)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "88aa9980-1bd6-4cc9-aeac-4c9011e617fc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### vision Support"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "79e372e3-7050-4038-bf88-d1e8f5ddae09",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "c2372365-7208-42f9-a147-deffdc390313",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The image depicts a charming Christmas-themed arrangement set against a rustic wooden backdrop, creating a warm and festive atmosphere. Here's a detailed breakdown:\n",
|
||||
"\n",
|
||||
"### **Background & Setting**\n",
|
||||
"- **Wooden Wall**: A horizontally paneled wooden wall forms the backdrop, giving a cozy, cabin-like feel.\n",
|
||||
"- **Foreground Surface**: The decorations rest on a smooth wooden surface (likely a table or desk), enhancing the natural, earthy tone of the scene.\n",
|
||||
"\n",
|
||||
"### **Key Elements**\n",
|
||||
"1. **Snow-Covered Trees**:\n",
|
||||
" - Two miniature evergreen trees dusted with artificial snow flank the sides of the arrangement, evoking a wintry landscape.\n",
|
||||
"\n",
|
||||
"2. **String Lights**:\n",
|
||||
" - A strand of white bulb lights stretches across the back, weaving through the decor and adding a soft, glowing ambiance.\n",
|
||||
"\n",
|
||||
"3. **Ornamental Sphere**:\n",
|
||||
" - A reflective gold sphere with striped patterns sits near the center-left, catching and dispersing light.\n",
|
||||
"\n",
|
||||
"4. **\"Merry Christmas\" Sign**:\n",
|
||||
" - A wooden cutout spelling \"MERRY CHRISTMAS\" in capital letters serves as the focal point. The letters feature star-shaped cutouts, allowing light to shine through.\n",
|
||||
"\n",
|
||||
"5. **Reindeer Figurine**:\n",
|
||||
" - A brown reindeer with white facial markings and large antlers stands prominently on the right, facing forward and adding a playful touch.\n",
|
||||
"\n",
|
||||
"6. **Candle Holders**:\n",
|
||||
" - Three birch-bark candle holders are arranged in front of the reindeer. Two hold lit tealights, casting a warm glow, while the third remains unlit.\n",
|
||||
"\n",
|
||||
"7. **Natural Accents**:\n",
|
||||
" - **Pinecones**: Scattered throughout, adding texture and a woodland feel.\n",
|
||||
" - **Berry Branches**: Red-berried greenery (likely holly) weaves behind the sign, introducing vibrant color.\n",
|
||||
" - **Pine Branches**: Fresh-looking branches enhance the seasonal authenticity.\n",
|
||||
"\n",
|
||||
"8. **Gift Box**:\n",
|
||||
" - A small golden gift box with a bow sits near the left, symbolizing holiday gifting.\n",
|
||||
"\n",
|
||||
"9. **Textile Detail**:\n",
|
||||
" - A fabric piece with \"Christmas\" embroidered on it peeks from the left, partially obscured but contributing to the thematic unity.\n",
|
||||
"\n",
|
||||
"### **Color Palette & Mood**\n",
|
||||
"- **Warm Tones**: Browns (wood, reindeer), golds (ornament, gift box), and whites (snow, lights) dominate, creating a inviting glow.\n",
|
||||
"- **Cool Accents**: Greens (trees, branches) and reds (berries) provide contrast, balancing the warmth.\n",
|
||||
"- **Lighting**: The lit candles and string lights cast a soft, flickering illumination, enhancing the intimate, celebratory vibe.\n",
|
||||
"\n",
|
||||
"### **Composition**\n",
|
||||
"- **Balance**: The arrangement is symmetrical, with trees and candles on either side framing the central sign and reindeer.\n",
|
||||
"- **Depth**: Layered elements (trees, lights, branches) create visual interest, drawing the eye inward.\n",
|
||||
"\n",
|
||||
"This image beautifully captures the essence of a cozy, handmade Christmas display, blending traditional symbols with natural textures to evoke nostalgia and joy.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.messages import HumanMessage\n",
|
||||
"\n",
|
||||
"model = ChatQwQ(model=\"qvq-max-latest\")\n",
|
||||
"\n",
|
||||
"messages = [\n",
|
||||
" HumanMessage(\n",
|
||||
" content=[\n",
|
||||
" {\n",
|
||||
" \"type\": \"image_url\",\n",
|
||||
" \"image_url\": {\"url\": \"https://example.com/image/image.png\"},\n",
|
||||
" },\n",
|
||||
" {\"type\": \"text\", \"text\": \"What do you see in this image?\"},\n",
|
||||
" ]\n",
|
||||
" )\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"response = model.invoke(messages)\n",
|
||||
"print(response.content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9242acf7-9a66-40b1-98b5-b113d28fc6ec",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Video"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "f0a9e542-7a85-44d2-8576-14314a50d948",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The image provided is a still frame from a video featuring a young woman with short brown hair and bangs, smiling brightly at the camera. Here's a detailed breakdown:\n",
|
||||
"\n",
|
||||
"### **Description of the Image:**\n",
|
||||
"- **Subject:** A youthful female with a cheerful expression, showcasing a wide smile with visible teeth.\n",
|
||||
"- **Appearance:** \n",
|
||||
" - Short, neatly styled brown hair with blunt bangs.\n",
|
||||
" - Natural makeup emphasizing clear skin and subtle eye makeup.\n",
|
||||
" - Wearing a white round-neck shirt layered under a light pink knitted cardigan.\n",
|
||||
" - Accessories include a delicate necklace with a small pendant and small earrings.\n",
|
||||
"- **Background:** An outdoor setting with blurred architectural elements (e.g., buildings with columns), suggesting a campus, park, or residential area.\n",
|
||||
"- **Lighting:** Soft, natural daylight, enhancing the warm and inviting atmosphere.\n",
|
||||
"\n",
|
||||
"### **Key Details About the Video:**\n",
|
||||
"1. **AI-Generated Content:** The watermark (\"通义·AI合成\" / \"Tongyi AI Synthesis\") indicates this image was created using Alibaba's Tongyi AI model, known for generating hyper-realistic visuals.\n",
|
||||
"2. **Style & Purpose:** The high-quality, photorealistic style suggests the video may demonstrate AI imaging capabilities, potentially for advertising, entertainment, or educational purposes.\n",
|
||||
"3. **Context Clues:** The subject's casual yet polished look and the pleasant outdoor setting imply a positive, approachable theme (e.g., lifestyle, technology promotion, or social media content).\n",
|
||||
"\n",
|
||||
"### **What We Can Infer About the Video:**\n",
|
||||
"- Likely showcases dynamic AI-generated scenes featuring the same character in various poses or interactions.\n",
|
||||
"- May highlight realism in digital avatars or synthetic media.\n",
|
||||
"- Could be part of a demo reel, tutorial, or creative project emphasizing AI artistry.\n",
|
||||
"\n",
|
||||
"### **Limitations:**\n",
|
||||
"- As only a single frame is provided, specifics about the video's length, narrative, or additional scenes cannot be determined.\n",
|
||||
"\n",
|
||||
"If you have more frames or context, feel free to share! 😊\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.messages import HumanMessage\n",
|
||||
"\n",
|
||||
"model = ChatQwQ(model=\"qvq-max-latest\")\n",
|
||||
"\n",
|
||||
"messages = [\n",
|
||||
" HumanMessage(\n",
|
||||
" content=[\n",
|
||||
" {\n",
|
||||
" \"type\": \"video_url\",\n",
|
||||
" \"video_url\": {\"url\": \"https://example.com/video/1.mp4\"},\n",
|
||||
" },\n",
|
||||
" {\"type\": \"text\", \"text\": \"Can you tell me about this video?\"},\n",
|
||||
" ]\n",
|
||||
" )\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"response = model.invoke(messages)\n",
|
||||
"print(response.content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
|
||||
@@ -258,11 +423,19 @@
|
||||
"\n",
|
||||
"For detailed documentation of all ChatQwQ features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "824f0c67-5f3b-4079-bc17-2cf92755bdd5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
@@ -276,7 +449,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.13.1"
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in New Issue
Block a user