mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
30151c99c7
As noted in prior PRs (https://github.com/hwchase17/langchain/pull/6060, https://github.com/hwchase17/langchain/pull/7348), the input/output format has changed a few times as we've stabilized our inference API. This PR updates the API to the latest stable version as indicated in our docs: https://docs.mosaicml.com/en/latest/inference.html The input format looks like this: `{"inputs": [<prompt>]} ` The output format looks like this: ` {"outputs": [<output_text>]} ` --------- Co-authored-by: Bagatur <baskaryan@gmail.com>
106 lines
2.3 KiB
Plaintext
106 lines
2.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# MosaicML\n",
|
|
"\n",
|
|
"[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n",
|
|
"\n",
|
|
"This example goes over how to use LangChain to interact with MosaicML Inference for text completion."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# sign up for an account: https://forms.mosaicml.com/demo?utm_source=langchain\n",
|
|
"\n",
|
|
"from getpass import getpass\n",
|
|
"\n",
|
|
"MOSAICML_API_TOKEN = getpass()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"\n",
|
|
"os.environ[\"MOSAICML_API_TOKEN\"] = MOSAICML_API_TOKEN"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.llms import MosaicML\n",
|
|
"from langchain import PromptTemplate, LLMChain"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"template = \"\"\"Question: {question}\"\"\"\n",
|
|
"\n",
|
|
"prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"llm = MosaicML(inject_instruction_format=True, model_kwargs={\"max_new_tokens\": 128})"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"llm_chain = LLMChain(prompt=prompt, llm=llm)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"question = \"What is one good reason why you should train a large language model on domain specific data?\"\n",
|
|
"\n",
|
|
"llm_chain.run(question)"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|