mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
021bb9be84
Hey, I'm a Modal Labs engineer and I'm making this docs update after getting a user question in [our beta Slack space](https://join.slack.com/t/modalbetatesters/shared_invite/zt-1xl9gbob8-1QDgUY7_PRPg6dQ49hqEeQ) about the Langchain integration docs. 🔗 [Modal beta-testers link to docs discussion thread](https://modalbetatesters.slack.com/archives/C031Z7DBQFL/p1689777700594819?thread_ts=1689775859.855849&cid=C031Z7DBQFL)
96 lines
2.6 KiB
Plaintext
96 lines
2.6 KiB
Plaintext
# Modal
|
|
|
|
This page covers how to use the Modal ecosystem to run LangChain custom LLMs.
|
|
It is broken into two parts:
|
|
|
|
1. Modal installation and web endpoint deployment
|
|
2. Using deployed web endpoint with `LLM` wrapper class.
|
|
|
|
## Installation and Setup
|
|
|
|
- Install with `pip install modal`
|
|
- Run `modal token new`
|
|
|
|
## Define your Modal Functions and Webhooks
|
|
|
|
You must include a prompt. There is a rigid response structure:
|
|
|
|
```python
|
|
class Item(BaseModel):
|
|
prompt: str
|
|
|
|
@stub.function()
|
|
@modal.web_endpoint(method="POST")
|
|
def get_text(item: Item):
|
|
return {"prompt": run_gpt2.call(item.prompt)}
|
|
```
|
|
|
|
The following is an example with the GPT2 model:
|
|
|
|
```python
|
|
from pydantic import BaseModel
|
|
|
|
import modal
|
|
|
|
CACHE_PATH = "/root/model_cache"
|
|
|
|
class Item(BaseModel):
|
|
prompt: str
|
|
|
|
stub = modal.Stub(name="example-get-started-with-langchain")
|
|
|
|
def download_model():
|
|
from transformers import GPT2Tokenizer, GPT2LMHeadModel
|
|
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
|
|
model = GPT2LMHeadModel.from_pretrained('gpt2')
|
|
tokenizer.save_pretrained(CACHE_PATH)
|
|
model.save_pretrained(CACHE_PATH)
|
|
|
|
# Define a container image for the LLM function below, which
|
|
# downloads and stores the GPT-2 model.
|
|
image = modal.Image.debian_slim().pip_install(
|
|
"tokenizers", "transformers", "torch", "accelerate"
|
|
).run_function(download_model)
|
|
|
|
@stub.function(
|
|
gpu="any",
|
|
image=image,
|
|
retries=3,
|
|
)
|
|
def run_gpt2(text: str):
|
|
from transformers import GPT2Tokenizer, GPT2LMHeadModel
|
|
tokenizer = GPT2Tokenizer.from_pretrained(CACHE_PATH)
|
|
model = GPT2LMHeadModel.from_pretrained(CACHE_PATH)
|
|
encoded_input = tokenizer(text, return_tensors='pt').input_ids
|
|
output = model.generate(encoded_input, max_length=50, do_sample=True)
|
|
return tokenizer.decode(output[0], skip_special_tokens=True)
|
|
|
|
@stub.function()
|
|
@modal.web_endpoint(method="POST")
|
|
def get_text(item: Item):
|
|
return {"prompt": run_gpt2.call(item.prompt)}
|
|
```
|
|
|
|
### Deploy the web endpoint
|
|
|
|
Deploy the web endpoint to Modal cloud with the [`modal deploy`](https://modal.com/docs/reference/cli/deploy) CLI command.
|
|
Your web endpoint will acquire a persistent URL under the `modal.run` domain.
|
|
|
|
## LLM wrapper around Modal web endpoint
|
|
|
|
The `Modal` LLM wrapper class which will accept your deployed web endpoint's URL.
|
|
|
|
```python
|
|
from langchain.llms import Modal
|
|
|
|
endpoint_url = "https://ecorp--custom-llm-endpoint.modal.run" # REPLACE ME with your deployed Modal web endpoint's URL
|
|
|
|
llm = Modal(endpoint_url=endpoint_url)
|
|
llm_chain = LLMChain(prompt=prompt, llm=llm)
|
|
|
|
question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"
|
|
|
|
llm_chain.run(question)
|
|
```
|
|
|