Duplicate from blobba/sentence-transformers-test-3

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+venv
+__pycache__

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860", "--workers=4"]

README.md

@@ -0,0 +1,9 @@
+---
+title: Fastapi Dummy
+emoji: 🐢
+colorFrom: purple
+colorTo: blue
+sdk: docker
+pinned: false
+duplicated_from: blobba/sentence-transformers-test-3
+---

justfile

@@ -0,0 +1,8 @@
+set fallback
+
+run:
+
+dev:
+    source venv/bin/activate
+    nix-shell
+    uvicorn src.main:app --reload

main.py

@@ -0,0 +1,45 @@
+from typing import Generic, List, Optional, TypeVar
+from functools import partial
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer
+from fastapi import FastAPI
+import numpy
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import ORJSONResponse
+
+MODEL = SentenceTransformer("all-mpnet-base-v2")
+
+def cache(func):
+    inner_cache = dict()
+    def inner(sentences: List[str]):
+        if len(sentences) == 0:
+            return []
+        not_in_cache = list(filter(lambda s: s not in inner_cache.keys(), sentences))
+        if len(not_in_cache) > 0:
+            processed_sentences = func(list(not_in_cache))
+            for sentence, embedding in zip(not_in_cache, processed_sentences):
+                inner_cache[sentence] = embedding
+        return [inner_cache[s] for s in sentences]
+    return inner
+
+@cache
+def _encode(sentences: List[str]):
+    embeddings = MODEL.encode(sentences, normalize_embeddings=True, batch_size=2, show_progress_bar=True)
+    array = [numpy.around(a, 3).tolist() for a in embeddings]
+    return array
+
+class EmbedReq(BaseModel):
+    sentences: List[str]
+
+app = FastAPI()
+
+@app.post("/embed", response_class=ORJSONResponse)
+def embed(embed: EmbedReq):
+    return _encode(embed.sentences)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)

requirements.txt

@@ -0,0 +1,7 @@
+sentence-transformers==2.2
+numpy==1.24
+joblib==1.2
+fastapi==0.89
+uvicorn[standard]==0.20
+huggingface-hub==0.10.1
+orjson==3.8.9

shell.nix

@@ -0,0 +1,31 @@
+with import <nixpkgs> {};
+mkShell {
+  packages = [
+    rustup
+    cargo
+
+    openssl
+    cacert
+    libiconv
+    pkg-config
+    libunistring
+    openblas
+    gfortran
+    gcc
+    sentencepiece
+    python39Packages.sentencepiece
+
+    wget
+
+    xz
+    gzip
+    bzip2
+    curlFull
+  ];
+  buildInputs = [] ++ lib.optionals stdenv.isDarwin [ 
+      darwin.apple_sdk.frameworks.IOKit
+      darwin.apple_sdk.frameworks.Security
+      darwin.apple_sdk.frameworks.CoreServices
+      darwin.apple_sdk.frameworks.CoreFoundation
+  ] ;
+}