mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-07 22:11:51 +00:00
Add Minimax llm model to langchain (#7645)
- Description: Minimax is a great AI startup from China, recently they released their latest model and chat API, and the API is widely-spread in China. As a result, I'd like to add the Minimax llm model to Langchain. - Tag maintainer: @hwchase17, @baskaryan --------- Co-authored-by: the <tao.he@hulu.com> Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit is contained in:
HeTaoPKU
GitHub
176
docs/extras/integrations/llms/minimax.ipynb
Normal file
176
docs/extras/integrations/llms/minimax.ipynb
Normal file
@@ -0,0 +1,176 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Minimax\n",
|
||||
"\n",
|
||||
"[Minimax](https://api.minimax.chat) is a Chinese startup that provides natural language processing models for companies and individuals.\n",
|
||||
"\n",
|
||||
"This example demonstrates using Langchain to interact with Minimax."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Setup\n",
|
||||
"\n",
|
||||
"To run this notebook, you'll need a [Minimax account](https://api.minimax.chat), an [API key](https://api.minimax.chat/user-center/basic-information/interface-key), and a [Group ID](https://api.minimax.chat/user-center/basic-information)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Single model call"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import Minimax"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 34,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Load the model\n",
|
||||
"minimax = Minimax(minimax_api_key=\"YOUR_API_KEY\", minimax_group_id=\"YOUR_GROUP_ID\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Prompt the model\n",
|
||||
"minimax(\"What is the difference between panda and bear?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Chained model calls"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# get api_key and group_id: https://api.minimax.chat/user-center/basic-information\n",
|
||||
"# We need `MINIMAX_API_KEY` and `MINIMAX_GROUP_ID`\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"MINIMAX_API_KEY\"] = \"YOUR_API_KEY\"\n",
|
||||
"os.environ[\"MINIMAX_GROUP_ID\"] = \"YOUR_GROUP_ID\""
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import Minimax\n",
|
||||
"from langchain import PromptTemplate, LLMChain"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"Question: {question}\n",
|
||||
"\n",
|
||||
"Answer: Let's think step by step.\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = Minimax()"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_chain = LLMChain(prompt=prompt, llm=llm)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"question = \"What NBA team won the Championship in the year Jay Zhou was born?\"\n",
|
||||
"\n",
|
||||
"llm_chain.run(question)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"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": "3.10.4"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
25
docs/extras/integrations/providers/minimax.mdx
Normal file
25
docs/extras/integrations/providers/minimax.mdx
Normal file
@@ -0,0 +1,25 @@
|
||||
# Minimax
|
||||
|
||||
>[Minimax](https://api.minimax.chat) is a Chinese startup that provides natural language processing models
|
||||
> for companies and individuals.
|
||||
|
||||
## Installation and Setup
|
||||
Get a [Minimax api key](https://api.minimax.chat/user-center/basic-information/interface-key) and set it as an environment variable (`MINIMAX_API_KEY`)
|
||||
Get a [Minimax group id](https://api.minimax.chat/user-center/basic-information) and set it as an environment variable (`MINIMAX_GROUP_ID`)
|
||||
|
||||
|
||||
## LLM
|
||||
|
||||
There exists a Minimax LLM wrapper, which you can access with
|
||||
See a [usage example](/docs/modules/model_io/models/llms/integrations/minimax.html).
|
||||
|
||||
```python
|
||||
from langchain.llms import Minimax
|
||||
```
|
||||
|
||||
## Text Embedding Model
|
||||
|
||||
There exists a Minimax Embedding model, which you can access with
|
||||
```python
|
||||
from langchain.embeddings import MiniMaxEmbeddings
|
||||
```
|
||||
Reference in New Issue
Block a user