mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-07 05:52:15 +00:00
ibm: Add support for Chat Models (#22979)
This commit is contained in:
Mateusz Szewczyk
GitHub
585
docs/docs/integrations/chat/ibm_watsonx.ipynb
Normal file
585
docs/docs/integrations/chat/ibm_watsonx.ipynb
Normal file
@@ -0,0 +1,585 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "1c95cd76",
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "raw"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_label: IBM watsonx.ai\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "70996d8a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ChatWatsonx\n",
|
||||
"\n",
|
||||
">ChatWatsonx is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.\n",
|
||||
"\n",
|
||||
"The aim of these examples is to show how to communicate with `watsonx.ai` models using `LangChain` LLMs API."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ef7b088a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Overview\n",
|
||||
"\n",
|
||||
"### Integration details\n",
|
||||
"| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/openai) | Package downloads | Package latest |\n",
|
||||
"| :--- | :--- | :---: | :---: | :---: | :---: | :---: |\n",
|
||||
"| [ChatWatsonx](https://api.python.langchain.com/en/latest/ibm_api_reference.html) | [langchain-ibm](https://api.python.langchain.com/en/latest/ibm_api_reference.html) | ❌ | ❌ | ❌ |  |  |\n",
|
||||
"\n",
|
||||
"### Model features\n",
|
||||
"| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | Image input | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
|
||||
"| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |\n",
|
||||
"| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f406e092",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"To access IBM watsonx.ai models you'll need to create an IBM watsonx.ai account, get an API key, and install the `langchain-ibm` integration package.\n",
|
||||
"\n",
|
||||
"### Credentials\n",
|
||||
"\n",
|
||||
"The cell below defines the credentials required to work with watsonx Foundation Model inferencing.\n",
|
||||
"\n",
|
||||
"**Action:** Provide the IBM Cloud user API key. For details, see\n",
|
||||
"[Managing user API keys](https://cloud.ibm.com/docs/account?topic=account-userapikey&interface=ui)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "11d572a1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from getpass import getpass\n",
|
||||
"\n",
|
||||
"watsonx_api_key = getpass()\n",
|
||||
"os.environ[\"WATSONX_APIKEY\"] = watsonx_api_key"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c59782a7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Additionally you are able to pass additional secrets as an environment variable. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f98c573c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"WATSONX_URL\"] = \"your service instance url\"\n",
|
||||
"os.environ[\"WATSONX_TOKEN\"] = \"your token for accessing the CPD cluster\"\n",
|
||||
"os.environ[\"WATSONX_PASSWORD\"] = \"your password for accessing the CPD cluster\"\n",
|
||||
"os.environ[\"WATSONX_USERNAME\"] = \"your username for accessing the CPD cluster\"\n",
|
||||
"os.environ[\"WATSONX_INSTANCE_ID\"] = \"your instance_id for accessing the CPD cluster\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b3dc9176",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Installation\n",
|
||||
"\n",
|
||||
"The LangChain IBM integration lives in the `langchain-ibm` package:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "387eda86",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install -qU langchain-ibm"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e36acbef",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Instantiation\n",
|
||||
"\n",
|
||||
"You might need to adjust model `parameters` for different models or tasks. For details, refer to [Available MetaNames](https://ibm.github.io/watsonx-ai-python-sdk/fm_model.html#metanames.GenTextParamsMetaNames)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "407cd500",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"parameters = {\n",
|
||||
" \"decoding_method\": \"sample\",\n",
|
||||
" \"max_new_tokens\": 100,\n",
|
||||
" \"min_new_tokens\": 1,\n",
|
||||
" \"stop_sequences\": [\".\"],\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2b586538",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Initialize the `WatsonxLLM` class with the previously set parameters.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"**Note**: \n",
|
||||
"\n",
|
||||
"- To provide context for the API call, you must pass the `project_id` or `space_id`. To get your project or space ID, open your project or space, go to the **Manage** tab, and click **General**. For more information see: [Project documentation](https://www.ibm.com/docs/en/watsonx-as-a-service?topic=projects) or [Deployment space documentation](https://www.ibm.com/docs/en/watsonx/saas?topic=spaces-creating-deployment).\n",
|
||||
"- Depending on the region of your provisioned service instance, use one of the urls listed in [watsonx.ai API Authentication](https://ibm.github.io/watsonx-ai-python-sdk/setup_cloud.html#authentication).\n",
|
||||
"\n",
|
||||
"In this example, we’ll use the `project_id` and Dallas URL.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"You need to specify the `model_id` that will be used for inferencing. You can find the list of all the available models in [Supported foundation models](https://ibm.github.io/watsonx-ai-python-sdk/fm_model.html#ibm_watsonx_ai.foundation_models.utils.enums.ModelTypes)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "98371396",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_ibm import ChatWatsonx\n",
|
||||
"\n",
|
||||
"chat = ChatWatsonx(\n",
|
||||
" model_id=\"ibm/granite-13b-chat-v2\",\n",
|
||||
" url=\"https://us-south.ml.cloud.ibm.com\",\n",
|
||||
" project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
|
||||
" params=parameters,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2202f4e0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Alternatively, you can use Cloud Pak for Data credentials. For details, see [watsonx.ai software setup](https://ibm.github.io/watsonx-ai-python-sdk/setup_cpd.html). "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "243ecccb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat = ChatWatsonx(\n",
|
||||
" model_id=\"ibm/granite-13b-chat-v2\",\n",
|
||||
" url=\"PASTE YOUR URL HERE\",\n",
|
||||
" username=\"PASTE YOUR USERNAME HERE\",\n",
|
||||
" password=\"PASTE YOUR PASSWORD HERE\",\n",
|
||||
" instance_id=\"openshift\",\n",
|
||||
" version=\"4.8\",\n",
|
||||
" project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
|
||||
" params=parameters,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "96ed13d4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Instead of `model_id`, you can also pass the `deployment_id` of the previously tuned model. The entire model tuning workflow is described in [Working with TuneExperiment and PromptTuner](https://ibm.github.io/watsonx-ai-python-sdk/pt_working_with_class_and_prompt_tuner.html)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "08e66c88",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat = ChatWatsonx(\n",
|
||||
" deployment_id=\"PASTE YOUR DEPLOYMENT_ID HERE\",\n",
|
||||
" url=\"https://us-south.ml.cloud.ibm.com\",\n",
|
||||
" project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
|
||||
" params=parameters,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f571001d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Invocation\n",
|
||||
"\n",
|
||||
"To obtain completions, you can call the model directly using a string prompt."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"id": "beea2b5b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content=\"Je t'aime pour écouter la Rock.\", response_metadata={'token_usage': {'generated_token_count': 12, 'input_token_count': 28}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-05b305ce-5401-4a10-b557-41a4b15c7f6f-0')"
|
||||
]
|
||||
},
|
||||
"execution_count": 22,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Invocation\n",
|
||||
"\n",
|
||||
"messages = [\n",
|
||||
" (\"system\", \"You are a helpful assistant that translates English to French.\"),\n",
|
||||
" (\n",
|
||||
" \"human\",\n",
|
||||
" \"I love you for listening to Rock.\",\n",
|
||||
" ),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"chat.invoke(messages)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 41,
|
||||
"id": "8ab1a25a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Sure, I can help you with that! Horses are large, powerful mammals that belong to the family Equidae.', response_metadata={'token_usage': {'generated_token_count': 24, 'input_token_count': 24}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-391776ff-3b38-4768-91e8-ff64177149e5-0')"
|
||||
]
|
||||
},
|
||||
"execution_count": 41,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Invocation multiple chat\n",
|
||||
"from langchain_core.messages import (\n",
|
||||
" HumanMessage,\n",
|
||||
" SystemMessage,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"system_message = SystemMessage(\n",
|
||||
" content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
|
||||
")\n",
|
||||
"human_message = HumanMessage(content=\"horse\")\n",
|
||||
"\n",
|
||||
"chat.invoke([system_message, human_message])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "20e4b568",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Chaining\n",
|
||||
"Create `ChatPromptTemplate` objects which will be responsible for creating a random question."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"id": "dd919925",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_core.prompts import ChatPromptTemplate\n",
|
||||
"\n",
|
||||
"system = (\n",
|
||||
" \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
|
||||
")\n",
|
||||
"human = \"{input}\"\n",
|
||||
"prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1a013a53",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Provide a inputs and run the chain."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"id": "68160377",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Ich liebe Python.', response_metadata={'token_usage': {'generated_token_count': 5, 'input_token_count': 23}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-1b1ccf5d-0e33-46f2-a087-e2a136ba1fb7-0')"
|
||||
]
|
||||
},
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain = prompt | chat\n",
|
||||
"chain.invoke(\n",
|
||||
" {\n",
|
||||
" \"input_language\": \"English\",\n",
|
||||
" \"output_language\": \"German\",\n",
|
||||
" \"input\": \"I love Python\",\n",
|
||||
" }\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d2c9da33",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Streaming the Model output \n",
|
||||
"\n",
|
||||
"You can stream the model output."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "3f63166a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The moon is a natural satellite of the Earth, and it has been a source of fascination for humans for centuries."
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"system_message = SystemMessage(\n",
|
||||
" content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
|
||||
")\n",
|
||||
"human_message = HumanMessage(content=\"moon\")\n",
|
||||
"\n",
|
||||
"for chunk in chat.stream([system_message, human_message]):\n",
|
||||
" print(chunk.content, end=\"\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5a7a2aa1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Batch the Model output \n",
|
||||
"\n",
|
||||
"You can batch the model output."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"id": "9e948729",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[AIMessage(content='Cats are domestic animals that belong to the Felidae family.', response_metadata={'token_usage': {'generated_token_count': 13, 'input_token_count': 24}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-71a8bd7a-a1aa-497b-9bdd-a4d6fe1d471a-0'),\n",
|
||||
" AIMessage(content='Dogs are domesticated mammals of the family Canidae, characterized by their adaptability to various environments and social structures.', response_metadata={'token_usage': {'generated_token_count': 24, 'input_token_count': 24}, 'model_name': 'ibm/granite-13b-chat-v2', 'system_fingerprint': '', 'finish_reason': 'stop_sequence'}, id='run-22b7a0cb-e44a-4b68-9921-872f82dcd82b-0')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 32,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"message_1 = [\n",
|
||||
" SystemMessage(\n",
|
||||
" content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
|
||||
" ),\n",
|
||||
" HumanMessage(content=\"cat\"),\n",
|
||||
"]\n",
|
||||
"message_2 = [\n",
|
||||
" SystemMessage(\n",
|
||||
" content=\"You are a helpful assistant which telling short-info about provided topic.\"\n",
|
||||
" ),\n",
|
||||
" HumanMessage(content=\"dog\"),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"chat.batch([message_1, message_2])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c739e1fe",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Tool calling\n",
|
||||
"\n",
|
||||
"### ChatWatsonx.bind_tools()\n",
|
||||
"\n",
|
||||
"Please note that `ChatWatsonx.bind_tools` is on beta state, so right now we only support `mistralai/mixtral-8x7b-instruct-v01` model.\n",
|
||||
"\n",
|
||||
"You should also redefine `max_new_tokens` parameter to get the entire model response. By default `max_new_tokens` is set ot 20."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "328fce76",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_ibm import ChatWatsonx\n",
|
||||
"\n",
|
||||
"parameters = {\"max_new_tokens\": 200}\n",
|
||||
"\n",
|
||||
"chat = ChatWatsonx(\n",
|
||||
" model_id=\"mistralai/mixtral-8x7b-instruct-v01\",\n",
|
||||
" url=\"https://us-south.ml.cloud.ibm.com\",\n",
|
||||
" project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
|
||||
" params=parameters,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "e1633a73",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_core.pydantic_v1 import BaseModel, Field\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"class GetWeather(BaseModel):\n",
|
||||
" \"\"\"Get the current weather in a given location\"\"\"\n",
|
||||
"\n",
|
||||
" location: str = Field(..., description=\"The city and state, e.g. San Francisco, CA\")\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"llm_with_tools = chat.bind_tools([GetWeather])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "3bf9b8ab",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='', additional_kwargs={'function_call': {'type': 'function'}, 'tool_calls': [{'type': 'function', 'function': {'name': 'GetWeather', 'arguments': '{\"location\": \"Los Angeles\"}'}, 'id': None}, {'type': 'function', 'function': {'name': 'GetWeather', 'arguments': '{\"location\": \"New York\"}'}, 'id': None}]}, response_metadata={'token_usage': {'generated_token_count': 99, 'input_token_count': 320}, 'model_name': 'mistralai/mixtral-8x7b-instruct-v01', 'system_fingerprint': '', 'finish_reason': 'eos_token'}, id='run-38627104-f2ac-4edb-8390-d5425fb65979-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'Los Angeles'}, 'id': None}, {'name': 'GetWeather', 'args': {'location': 'New York'}, 'id': None}])"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"ai_msg = llm_with_tools.invoke(\n",
|
||||
" \"Which city is hotter today: LA or NY?\",\n",
|
||||
")\n",
|
||||
"ai_msg"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ba03dbf4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### AIMessage.tool_calls\n",
|
||||
"Notice that the AIMessage has a `tool_calls` attribute. This contains in a standardized ToolCall format that is model-provider agnostic."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "38f10ba7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[{'name': 'GetWeather', 'args': {'location': 'Los Angeles'}, 'id': None},\n",
|
||||
" {'name': 'GetWeather', 'args': {'location': 'New York'}, 'id': None}]"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"ai_msg.tool_calls"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9ee72a59",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## API reference\n",
|
||||
"\n",
|
||||
"For detailed documentation of all IBM watsonx.ai features and configurations head to the API reference: https://api.python.langchain.com/en/latest/ibm_api_reference.html"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.10.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -28,6 +28,16 @@ import os
|
||||
os.environ["WATSONX_APIKEY"] = "your IBM watsonx.ai api key"
|
||||
```
|
||||
|
||||
## Chat Model
|
||||
|
||||
### ChatWatsonx
|
||||
|
||||
See a [usage example](/docs/integrations/chat/ibm_watsonx).
|
||||
|
||||
```python
|
||||
from langchain_ibm import ChatWatsonx
|
||||
```
|
||||
|
||||
## LLMs
|
||||
|
||||
### WatsonxLLM
|
||||
|
||||
Reference in New Issue
Block a user