feat(conda):Add seperate env for huggingface (#1146)

**Description** This PR is related to #1117 **Notes for Reviewers** * Add conda env `huggingface.yml` * Change the import order, and also remove the no-used packages * Add `run.sh` and `make command` to the main Dockerfile and Makefile * Add test cases for it. It can be triggered and succeed under VSCode Python extension but it is hang by using `python -m unites test_huggingface.py` in the terminal ``` Running tests (unittest): /workspaces/LocalAI/extra/grpc/huggingface Running tests: /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_embedding /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_load_model /workspaces/LocalAI/extra/grpc/huggingface/test_huggingface.py::TestBackendServicer::test_server_startup ./test_huggingface.py::TestBackendServicer::test_embedding Passed ./test_huggingface.py::TestBackendServicer::test_load_model Passed ./test_huggingface.py::TestBackendServicer::test_server_startup Passed Total number of tests expected to run: 3 Total number of tests run: 3 Total number of tests passed: 3 Total number of tests failed: 0 Total number of tests failed with errors: 0 Total number of tests skipped: 0 Finished running tests! ``` **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [x] Yes, I signed my commits.  Signed-off-by: GitHub <[email protected]>
mudler · Oct 9, 2023 · 13eba81 · 13eba81
1 parent 5cff84b
commit 13eba81
Show file tree

Hide file tree

Showing 9 changed files with 253 additions and 6 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -11,7 +11,7 @@ ARG TARGETARCH
 ARG TARGETVARIANT
 
 ENV BUILD_TYPE=${BUILD_TYPE}
-ENV EXTERNAL_GRPC_BACKENDS="huggingface-embeddings:/build/extra/grpc/huggingface/huggingface.py,autogptq:/build/extra/grpc/autogptq/run.sh,bark:/build/extra/grpc/bark/run.sh,diffusers:/build/extra/grpc/diffusers/run.sh,exllama:/build/extra/grpc/exllama/exllama.py,vall-e-x:/build/extra/grpc/vall-e-x/ttsvalle.py,vllm:/build/extra/grpc/vllm/run.sh"
+ENV EXTERNAL_GRPC_BACKENDS="huggingface-embeddings:/build/extra/grpc/huggingface/run.sh,autogptq:/build/extra/grpc/autogptq/run.sh,bark:/build/extra/grpc/bark/run.sh,diffusers:/build/extra/grpc/diffusers/run.sh,exllama:/build/extra/grpc/exllama/exllama.py,vall-e-x:/build/extra/grpc/vall-e-x/ttsvalle.py,vllm:/build/extra/grpc/vllm/run.sh"
 ENV GALLERIES='[{"name":"model-gallery", "url":"github:go-skynet/model-gallery/index.yaml"}, {"url": "github:go-skynet/model-gallery/huggingface.yaml","name":"huggingface"}]'
 ARG GO_TAGS="stablediffusion tts"
 

diff --git a/Makefile b/Makefile
@@ -384,6 +384,7 @@ prepare-extra-conda-environments:
 	$(MAKE) -C extra/grpc/bark
 	$(MAKE) -C extra/grpc/diffusers
 	$(MAKE) -C extra/grpc/vllm
+	$(MAKE) -C extra/grpc/huggingface
 
 backend-assets/grpc:
 	mkdir -p backend-assets/grpc

diff --git a/extra/grpc/huggingface/Makefile b/extra/grpc/huggingface/Makefile
@@ -0,0 +1,18 @@
+.PONY: huggingface
+huggingface:
+	@echo "Creating virtual environment..."
+	@conda env create --name huggingface --file huggingface.yml
+	@echo "Virtual environment created."
+
+.PONY: run
+run:
+	@echo "Running huggingface..."
+	bash run.sh
+	@echo "huggingface run."
+
+# It is not working well by using command line. It only6 works with IDE like VSCode.
+.PONY: test
+test:
+	@echo "Testing huggingface..."
+	bash test.sh
+	@echo "huggingface tested."
diff --git a/extra/grpc/huggingface/README.md b/extra/grpc/huggingface/README.md
@@ -0,0 +1,5 @@
+# Creating a separate environment for the huggingface project
+
+```
+make huggingface
+```
diff --git a/extra/grpc/huggingface/huggingface.py b/extra/grpc/huggingface/huggingface.py
@@ -1,13 +1,20 @@
+"""
+Extra gRPC server for HuggingFace SentenceTransformer models.
+"""
 #!/usr/bin/env python3
-import grpc
 from concurrent import futures
-import time
-import backend_pb2
-import backend_pb2_grpc
+
 import argparse
 import signal
 import sys
 import os
+
+import time
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+
 from sentence_transformers import SentenceTransformer
 
 _ONE_DAY_IN_SECONDS = 60 * 60 * 24
@@ -17,18 +24,56 @@
 
 # Implement the BackendServicer class with the service methods
 class BackendServicer(backend_pb2_grpc.BackendServicer):
+    """
+    A gRPC servicer for the backend service.
+
+    This class implements the gRPC methods for the backend service, including Health, LoadModel, and Embedding.
+    """
     def Health(self, request, context):
+        """
+        A gRPC method that returns the health status of the backend service.
+
+        Args:
+            request: A HealthRequest object that contains the request parameters.
+            context: A grpc.ServicerContext object that provides information about the RPC.
+
+        Returns:
+            A Reply object that contains the health status of the backend service.
+        """
         return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
+
     def LoadModel(self, request, context):
+        """
+        A gRPC method that loads a model into memory.
+
+        Args:
+            request: A LoadModelRequest object that contains the request parameters.
+            context: A grpc.ServicerContext object that provides information about the RPC.
+
+        Returns:
+            A Result object that contains the result of the LoadModel operation.
+        """
         model_name = request.Model
         try:
             self.model = SentenceTransformer(model_name)
         except Exception as err:
             return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+
         # Implement your logic here for the LoadModel service
         # Replace this with your desired response
         return backend_pb2.Result(message="Model loaded successfully", success=True)
+
     def Embedding(self, request, context):
+        """
+        A gRPC method that calculates embeddings for a given sentence.
+
+        Args:
+            request: An EmbeddingRequest object that contains the request parameters.
+            context: A grpc.ServicerContext object that provides information about the RPC.
+
+        Returns:
+            An EmbeddingResult object that contains the calculated embeddings.
+        """
         # Implement your logic here for the Embedding service
         # Replace this with your desired response
         print("Calculated embeddings for: " + request.Embeddings, file=sys.stderr)
@@ -66,4 +111,4 @@ def signal_handler(sig, frame):
     )
     args = parser.parse_args()
 
-    serve(args.addr)
+    serve(args.addr)
diff --git a/extra/grpc/huggingface/huggingface.yml b/extra/grpc/huggingface/huggingface.yml
@@ -0,0 +1,77 @@
+name: huggingface
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - bzip2=1.0.8=h7b6447c_0
+  - ca-certificates=2023.08.22=h06a4308_0
+  - ld_impl_linux-64=2.38=h1181459_1
+  - libffi=3.4.4=h6a678d5_0
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libuuid=1.41.5=h5eee18b_0
+  - ncurses=6.4=h6a678d5_0
+  - openssl=3.0.11=h7f8727e_2
+  - pip=23.2.1=py311h06a4308_0
+  - python=3.11.5=h955ad1f_0
+  - readline=8.2=h5eee18b_0
+  - setuptools=68.0.0=py311h06a4308_0
+  - sqlite=3.41.2=h5eee18b_0
+  - tk=8.6.12=h1ccaba5_0
+  - tzdata=2023c=h04d1e81_0
+  - wheel=0.41.2=py311h06a4308_0
+  - xz=5.4.2=h5eee18b_0
+  - zlib=1.2.13=h5eee18b_0
+  - pip:
+      - certifi==2023.7.22
+      - charset-normalizer==3.3.0
+      - click==8.1.7
+      - filelock==3.12.4
+      - fsspec==2023.9.2
+      - grpcio==1.59.0
+      - huggingface-hub==0.17.3
+      - idna==3.4
+      - install==1.3.5
+      - jinja2==3.1.2
+      - joblib==1.3.2
+      - markupsafe==2.1.3
+      - mpmath==1.3.0
+      - networkx==3.1
+      - nltk==3.8.1
+      - numpy==1.26.0
+      - nvidia-cublas-cu12==12.1.3.1
+      - nvidia-cuda-cupti-cu12==12.1.105
+      - nvidia-cuda-nvrtc-cu12==12.1.105
+      - nvidia-cuda-runtime-cu12==12.1.105
+      - nvidia-cudnn-cu12==8.9.2.26
+      - nvidia-cufft-cu12==11.0.2.54
+      - nvidia-curand-cu12==10.3.2.106
+      - nvidia-cusolver-cu12==11.4.5.107
+      - nvidia-cusparse-cu12==12.1.0.106
+      - nvidia-nccl-cu12==2.18.1
+      - nvidia-nvjitlink-cu12==12.2.140
+      - nvidia-nvtx-cu12==12.1.105
+      - packaging==23.2
+      - pillow==10.0.1
+      - protobuf==4.24.4
+      - pyyaml==6.0.1
+      - regex==2023.10.3
+      - requests==2.31.0
+      - safetensors==0.4.0
+      - scikit-learn==1.3.1
+      - scipy==1.11.3
+      - sentence-transformers==2.2.2
+      - sentencepiece==0.1.99
+      - sympy==1.12
+      - threadpoolctl==3.2.0
+      - tokenizers==0.14.1
+      - torch==2.1.0
+      - torchvision==0.16.0
+      - tqdm==4.66.1
+      - transformers==4.34.0
+      - triton==2.1.0
+      - typing-extensions==4.8.0
+      - urllib3==2.0.6
+prefix: /opt/conda/envs/huggingface
diff --git a/extra/grpc/huggingface/run.sh b/extra/grpc/huggingface/run.sh
@@ -0,0 +1,10 @@
+##
+## A bash script wrapper that runs the huggingface server with conda
+
+# Activate conda environment
+source activate huggingface
+
+# get the directory where the bash script is located
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+
+python $DIR/huggingface.py
diff --git a/extra/grpc/huggingface/test.sh b/extra/grpc/huggingface/test.sh
@@ -0,0 +1,10 @@
+##
+## A bash script wrapper that runs the huggingface server with conda
+
+# Activate conda environment
+source activate huggingface
+
+# get the directory where the bash script is located
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+
+python -m unittest $DIR/test_huggingface.py
diff --git a/extra/grpc/huggingface/test_huggingface.py b/extra/grpc/huggingface/test_huggingface.py
@@ -0,0 +1,81 @@
+"""
+A test script to test the gRPC service
+"""
+import unittest
+import subprocess
+import time
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+
+
+class TestBackendServicer(unittest.TestCase):
+    """
+    TestBackendServicer is the class that tests the gRPC service
+    """
+    def setUp(self):
+        """
+        This method sets up the gRPC service by starting the server
+        """
+        self.service = subprocess.Popen(["python3", "huggingface.py", "--addr", "localhost:50051"])
+
+    def tearDown(self) -> None:
+        """
+        This method tears down the gRPC service by terminating the server
+        """
+        self.service.terminate()
+        self.service.wait()
+
+    def test_server_startup(self):
+        """
+        This method tests if the server starts up successfully
+        """
+        time.sleep(2)
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.Health(backend_pb2.HealthMessage())
+                self.assertEqual(response.message, b'OK')
+        except Exception as err:
+            print(err)
+            self.fail("Server failed to start")
+        finally:
+            self.tearDown()
+
+    def test_load_model(self):
+        """
+        This method tests if the model is loaded successfully
+        """
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.LoadModel(backend_pb2.ModelOptions(Model="bert-base-nli-mean-tokens"))
+                self.assertTrue(response.success)
+                self.assertEqual(response.message, "Model loaded successfully")
+        except Exception as err:
+            print(err)
+            self.fail("LoadModel service failed")
+        finally:
+            self.tearDown()
+
+    def test_embedding(self):
+        """
+        This method tests if the embeddings are generated successfully
+        """
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.LoadModel(backend_pb2.ModelOptions(Model="bert-base-nli-mean-tokens"))
+                self.assertTrue(response.success)
+                embedding_request = backend_pb2.PredictOptions(Embeddings="This is a test sentence.")
+                embedding_response = stub.Embedding(embedding_request)
+                self.assertIsNotNone(embedding_response.embeddings)
+        except Exception as err:
+            print(err)
+            self.fail("Embedding service failed")
+        finally:
+            self.tearDown()