Add finetuning component (opea-project#502)

Signed-off-by: Xinyu Ye <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: lkk <[email protected]>
Co-authored-by: test <[email protected]>
Co-authored-by: root <[email protected]>
Co-authored-by: Letong Han <[email protected]>
Signed-off-by: siddhivelankar23 <[email protected]>

comps/cores/mega/micro_service.py

@@ -3,7 +3,7 @@
 
 import asyncio
 import multiprocessing
-from typing import Any, Optional, Type
+from typing import Any, List, Optional, Type
 
 from ..proto.docarray import TextDoc
 from .constants import ServiceRoleType, ServiceType
@@ -154,6 +154,7 @@ def register_microservice(
     output_datatype: Type[Any] = TextDoc,
     provider: Optional[str] = None,
     provider_endpoint: Optional[str] = None,
+    methods: List[str] = ["POST"],
 ):
     def decorator(func):
         if name not in opea_microservices:
@@ -173,7 +174,8 @@ def decorator(func):
                 provider_endpoint=provider_endpoint,
             )
             opea_microservices[name] = micro_service
-        opea_microservices[name].app.router.add_api_route(endpoint, func, methods=["POST"])
+        opea_microservices[name].app.router.add_api_route(endpoint, func, methods=methods)
+
         return func
 
     return decorator

comps/cores/proto/api_protocol.py

@@ -539,3 +539,225 @@ def check_requests(request) -> Optional[JSONResponse]:
         )
 
     return None
+
+
+class Hyperparameters(BaseModel):
+    batch_size: Optional[Union[Literal["auto"], int]] = "auto"
+    """Number of examples in each batch.
+
+    A larger batch size means that model parameters are updated less frequently, but with lower variance.
+    """
+
+    learning_rate_multiplier: Optional[Union[Literal["auto"], float]] = "auto"
+    """Scaling factor for the learning rate.
+
+    A smaller learning rate may be useful to avoid overfitting.
+    """
+
+    n_epochs: Optional[Union[Literal["auto"], int]] = "auto"
+    """The number of epochs to train the model for.
+
+    An epoch refers to one full cycle through the training dataset. "auto" decides
+    the optimal number of epochs based on the size of the dataset. If setting the
+    number manually, we support any number between 1 and 50 epochs.
+    """
+
+
+class FineTuningJobWandbIntegration(BaseModel):
+    project: str
+    """The name of the project that the new run will be created under."""
+
+    entity: Optional[str] = None
+    """The entity to use for the run.
+
+    This allows you to set the team or username of the WandB user that you would
+    like associated with the run. If not set, the default entity for the registered
+    WandB API key is used.
+    """
+
+    name: Optional[str] = None
+    """A display name to set for the run.
+
+    If not set, we will use the Job ID as the name.
+    """
+
+    tags: Optional[List[str]] = None
+    """A list of tags to be attached to the newly created run.
+
+    These tags are passed through directly to WandB. Some default tags are generated
+    by OpenAI: "openai/finetune", "openai/{base-model}", "openai/{ftjob-abcdef}".
+    """
+
+
+class FineTuningJobWandbIntegrationObject(BaseModel):
+    type: Literal["wandb"]
+    """The type of the integration being enabled for the fine-tuning job."""
+
+    wandb: FineTuningJobWandbIntegration
+    """The settings for your integration with Weights and Biases.
+
+    This payload specifies the project that metrics will be sent to. Optionally, you
+    can set an explicit display name for your run, add tags to your run, and set a
+    default entity (team, username, etc) to be associated with your run.
+    """
+
+
+class FineTuningJobsRequest(BaseModel):
+    # Ordered by official OpenAI API documentation
+    # https://platform.openai.com/docs/api-reference/fine-tuning/create
+    model: str
+    """The name of the model to fine-tune."""
+
+    training_file: str
+    """The ID of an uploaded file that contains training data."""
+
+    hyperparameters: Optional[Hyperparameters] = None
+    """The hyperparameters used for the fine-tuning job."""
+
+    suffix: Optional[str] = None
+    """A string of up to 64 characters that will be added to your fine-tuned model name."""
+
+    validation_file: Optional[str] = None
+    """The ID of an uploaded file that contains validation data."""
+
+    integrations: Optional[List[FineTuningJobWandbIntegrationObject]] = None
+    """A list of integrations to enable for your fine-tuning job."""
+
+    seed: Optional[str] = None
+
+
+class Error(BaseModel):
+    code: str
+    """A machine-readable error code."""
+
+    message: str
+    """A human-readable error message."""
+
+    param: Optional[str] = None
+    """The parameter that was invalid, usually `training_file` or `validation_file`.
+
+    This field will be null if the failure was not parameter-specific.
+    """
+
+
+class FineTuningJob(BaseModel):
+    # Ordered by official OpenAI API documentation
+    # https://platform.openai.com/docs/api-reference/fine-tuning/object
+    id: str
+    """The object identifier, which can be referenced in the API endpoints."""
+
+    created_at: int
+    """The Unix timestamp (in seconds) for when the fine-tuning job was created."""
+
+    error: Optional[Error] = None
+    """For fine-tuning jobs that have `failed`, this will contain more information on
+    the cause of the failure."""
+
+    fine_tuned_model: Optional[str] = None
+    """The name of the fine-tuned model that is being created.
+
+    The value will be null if the fine-tuning job is still running.
+    """
+
+    finished_at: Optional[int] = None
+    """The Unix timestamp (in seconds) for when the fine-tuning job was finished.
+
+    The value will be null if the fine-tuning job is still running.
+    """
+
+    hyperparameters: Hyperparameters
+    """The hyperparameters used for the fine-tuning job.
+
+    See the [fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning)
+    for more details.
+    """
+
+    model: str
+    """The base model that is being fine-tuned."""
+
+    object: Literal["fine_tuning.job"] = "fine_tuning.job"
+    """The object type, which is always "fine_tuning.job"."""
+
+    organization_id: Optional[str] = None
+    """The organization that owns the fine-tuning job."""
+
+    result_files: List[str] = None
+    """The compiled results file ID(s) for the fine-tuning job.
+
+    You can retrieve the results with the
+    [Files API](https://platform.openai.com/docs/api-reference/files/retrieve-contents).
+    """
+
+    status: Literal["validating_files", "queued", "running", "succeeded", "failed", "cancelled"]
+    """The current status of the fine-tuning job, which can be either
+    `validating_files`, `queued`, `running`, `succeeded`, `failed`, or `cancelled`."""
+
+    trained_tokens: Optional[int] = None
+    """The total number of billable tokens processed by this fine-tuning job.
+
+    The value will be null if the fine-tuning job is still running.
+    """
+
+    training_file: str
+    """The file ID used for training.
+
+    You can retrieve the training data with the
+    [Files API](https://platform.openai.com/docs/api-reference/files/retrieve-contents).
+    """
+
+    validation_file: Optional[str] = None
+    """The file ID used for validation.
+
+    You can retrieve the validation results with the
+    [Files API](https://platform.openai.com/docs/api-reference/files/retrieve-contents).
+    """
+
+    integrations: Optional[List[FineTuningJobWandbIntegrationObject]] = None
+    """A list of integrations to enable for this fine-tuning job."""
+
+    seed: Optional[int] = None
+    """The seed used for the fine-tuning job."""
+
+    estimated_finish: Optional[int] = None
+    """The Unix timestamp (in seconds) for when the fine-tuning job is estimated to
+    finish.
+
+    The value will be null if the fine-tuning job is not running.
+    """
+
+
+class FineTuningJobIDRequest(BaseModel):
+    # Ordered by official OpenAI API documentation
+    # https://platform.openai.com/docs/api-reference/fine-tuning/retrieve
+    # https://platform.openai.com/docs/api-reference/fine-tuning/cancel
+    fine_tuning_job_id: str
+    """The ID of the fine-tuning job."""
+
+
+class FineTuningJobListRequest(BaseModel):
+    # Ordered by official OpenAI API documentation
+    # https://platform.openai.com/docs/api-reference/fine-tuning/list
+    after: Optional[str] = None
+    """Identifier for the last job from the previous pagination request."""
+
+    limit: Optional[int] = 20
+    """Number of fine-tuning jobs to retrieve."""
+
+
+class FineTuningJobList(BaseModel):
+    # Ordered by official OpenAI API documentation
+    # https://platform.openai.com/docs/api-reference/fine-tuning/list
+    object: str = "list"
+    """The object type, which is always "list".
+
+    This indicates that the returned data is a list of fine-tuning jobs.
+    """
+
+    data: List[FineTuningJob]
+    """A list containing FineTuningJob objects."""
+
+    has_more: bool
+    """Indicates whether there are more fine-tuning jobs beyond the current list.
+
+    If true, additional requests can be made to retrieve more jobs.
+    """

comps/finetuning/README.md

@@ -0,0 +1,121 @@
+# LLM Fine-tuning Microservice
+
+LLM Fine-tuning microservice involves adapting a base model to a specific task or dataset to improve its performance on that task.
+
+# 🚀1. Start Microservice with Python (Optional 1)
+
+## 1.1 Install Requirements
+
+```bash
+python -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+python -m pip install intel-extension-for-pytorch
+python -m pip install oneccl_bind_pt --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/
+pip install -r requirements.txt
+```
+
+## 1.2 Start Finetuning Service with Python Script
+
+### 1.2.1 Start Ray Cluster
+
+OneCCL and Intel MPI libraries should be dynamically linked in every node before Ray starts:
+
+```bash
+source $(python -c "import oneccl_bindings_for_pytorch as torch_ccl; print(torch_ccl.cwd)")/env/setvars.sh
+```
+
+Start Ray locally using the following command.
+
+```bash
+ray start --head
+```
+
+For a multi-node cluster, start additional Ray worker nodes with below command.
+
+```bash
+ray start --address='${head_node_ip}:6379'
+```
+
+### 1.2.2 Start Finetuning Service
+
+```bash
+export HF_TOKEN=${your_huggingface_token}
+python finetuning_service.py
+```
+
+# 🚀2. Start Microservice with Docker (Optional 2)
+
+## 2.1 Setup on CPU
+
+### 2.1.1 Build Docker Image
+
+Build docker image with below command:
+
+```bash
+export HF_TOKEN=${your_huggingface_token}
+cd ../../
+docker build -t opea/finetuning:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg HF_TOKEN=$HF_TOKEN -f comps/finetuning/docker/Dockerfile_cpu .
+```
+
+### 2.1.2 Run Docker with CLI
+
+Start docker container with below command:
+
+```bash
+docker run -d --name="finetuning-server" -p 8005:8005 --runtime=runc --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy opea/finetuning:latest
+```
+
+## 2.2 Setup on Gaudi2
+
+### 2.2.1 Build Docker Image
+
+Build docker image with below command:
+
+```bash
+cd ../../
+docker build -t opea/finetuning-gaudi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/finetuning/docker/Dockerfile_hpu .
+```
+
+### 2.2.2 Run Docker with CLI
+
+Start docker container with below command:
+
+```bash
+export HF_TOKEN=${your_huggingface_token}
+docker run --runtime=habana -e HABANA_VISIBLE_DEVICES=all -p 8005:8005 -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --ipc=host -e https_proxy=$https_proxy -e http_proxy=$http_proxy -e no_proxy=$no_proxy -e HF_TOKEN=$HF_TOKEN opea/finetuning-gaudi:latest
+```
+
+# 🚀3. Consume Finetuning Service
+
+## 3.1 Create fine-tuning job
+
+Assuming a training file `alpaca_data.json` is uploaded, it can be downloaded in [here](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json), the following script launches a finetuning job using `meta-llama/Llama-2-7b-chat-hf` as base model:
+
+```bash
+# upload a training file
+curl http://${your_ip}:8005/v1/finetune/upload_training_files -X POST -H "Content-Type: multipart/form-data" -F "files=@./alpaca_data.json"
+
+# create a finetuning job
+curl http://${your_ip}:8005/v1/fine_tuning/jobs \
+  -X POST \
+  -H "Content-Type: application/json" \
+  -d '{
+    "training_file": "alpaca_data.json",
+    "model": "meta-llama/Llama-2-7b-chat-hf"
+  }'
+
+# list finetuning jobs
+curl http://${your_ip}:8005/v1/fine_tuning/jobs   -X GET
+
+# retrieve one finetuning job
+curl http://localhost:8005/v1/fine_tuning/jobs/retrieve   -X POST   -H "Content-Type: application/json"   -d '{
+    "fine_tuning_job_id": ${fine_tuning_job_id}}'
+
+# cancel one finetuning job
+
+curl http://localhost:8005/v1/fine_tuning/jobs/cancel   -X POST   -H "Content-Type: application/json"   -d '{
+    "fine_tuning_job_id": ${fine_tuning_job_id}}'
+
+# list checkpoints of a finetuning job
+curl http://${your_ip}:8005/v1/finetune/list_checkpoints -X POST -H "Content-Type: application/json" -d '{"fine_tuning_job_id": ${fine_tuning_job_id}}'
+
+```