mirror of
https://github.com/hwchase17/langchain.git
synced 2025-07-16 17:53:37 +00:00
Added langchain-qwq package documentation (Alibaba Cloud) (#30628)
LangChain QwQ allows non-Tongyi users to access thinking models with extra capabilities which serve as an extension to Alibaba Cloud. Hi @ccurme I'm back with the updated PR this time with documentation and a finished package. - [x] **PR title**: "package: description" - Where "package" is whichever of langchain, community, core, etc. is being modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI changes. - Example: "community: add foobar LLM" - **Description:** adds documentation of `langchain-qwq` integration package. Also adds it to Alibaba Cloud provider - **Issue:** #30580 #30317 #30579 - **Dependencies:** openai, json-repair - **Twitter handle:** YigitBekir - [x] **Add tests and docs**: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [x] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
This commit is contained in:
Yiğit Bekir Kaya, PhD
GitHub
parent
4e7a9a7014
commit
87e82fe1e8
284
docs/docs/integrations/chat/qwq.ipynb
Normal file
284
docs/docs/integrations/chat/qwq.ipynb
Normal file
@ -0,0 +1,284 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "afaf8039",
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "raw"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_label: Qwen QwQ\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e49f1e0d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ChatQwQ\n",
|
||||
"\n",
|
||||
"This will help you getting started with QwQ [chat models](../../concepts/chat_models.mdx). For detailed documentation of all ChatQwQ 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",
|
||||
"| [ChatQwQ](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 QwQ 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": 2,
|
||||
"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": 3,
|
||||
"id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_qwq import ChatQwQ\n",
|
||||
"\n",
|
||||
"llm = ChatQwQ(\n",
|
||||
" model=\"qwq-plus\",\n",
|
||||
" max_tokens=3_000,\n",
|
||||
" timeout=None,\n",
|
||||
" max_retries=2,\n",
|
||||
" # other params...\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2b4f3e15",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Invocation"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "62e0dbc3",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"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': {}})"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"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": 5,
|
||||
"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': {}})"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"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",
|
||||
"ChatQwQ 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={'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"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.tools import tool\n",
|
||||
"from langchain_qwq import ChatQwQ\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 = ChatQwQ()\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": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## API reference\n",
|
||||
"\n",
|
||||
"For detailed documentation of all ChatQwQ features and configurations head to the [API reference](https://pypi.org/project/langchain-qwq/)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"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": "3.13.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -46,6 +46,14 @@ See [installation instructions and a usage example](/docs/integrations/chat/tong
|
||||
from langchain_community.chat_models.tongyi import ChatTongyi
|
||||
```
|
||||
|
||||
### Qwen QwQ Chat
|
||||
|
||||
See [installation instructions and a usage example](/docs/integrations/chat/qwq)
|
||||
|
||||
```python
|
||||
from langchain_qwq import ChatQwQ
|
||||
```
|
||||
|
||||
## Document Loaders
|
||||
|
||||
### Alibaba Cloud MaxCompute
|
||||
|
||||
@ -579,3 +579,7 @@ packages:
|
||||
- name: langchain-mariadb
|
||||
path: .
|
||||
repo: mariadb-corporation/langchain-mariadb
|
||||
- name: langchain-qwq
|
||||
path: .
|
||||
repo: yigit353/langchain-qwq
|
||||
provider_page: alibaba_cloud
|
||||
|
||||
Loading…
Reference in New Issue
Block a user