[feat]: initial commit

.gitignore

@@ -0,0 +1 @@
+venv

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.11
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,36 @@
+from sentence_transformers import CrossEncoder
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+app = FastAPI()
+
+class ChunkSimilarityRequest(BaseModel):
+    query: str
+    chunks: list[str]
+    top_k: int = 5
+
+
+model = CrossEncoder('cross-encoder/ms-marco-MiniLM-L6-v2')
+
+
+def cross_encoder_similarity(query, candidates):
+    pairs = [[query, candidate] for candidate in candidates]
+    scores = model.predict(pairs)
+    return scores
+
+
+
+@app.get("/keyword-similarity")
+async def cross_encoding_similarity():
+    return {"status": "success"}
+
+
+@app.post("/keyword-similarity")
+async def cross_encoding_similarity(
+    payload: ChunkSimilarityRequest
+):
+    scores = cross_encoder_similarity(payload.query, payload.chunks)
+
+    return [
+        chunk for chunk, _ in sorted(zip(payload.chunks, scores), key=lambda x: x[1], reverse=True)[:payload.top_k]
+    ]

requirements.txt

@@ -0,0 +1,57 @@
+annotated-types==0.7.0
+anyio==4.9.0
+certifi==2025.4.26
+charset-normalizer==3.4.2
+click==8.2.1
+fastapi==0.115.12
+filelock==3.18.0
+fsspec==2025.5.1
+h11==0.16.0
+hf-xet==1.1.3
+huggingface-hub==0.32.4
+idna==3.10
+Jinja2==3.1.6
+joblib==1.5.1
+MarkupSafe==3.0.2
+mpmath==1.3.0
+networkx==3.5
+numpy==2.2.6
+nvidia-cublas-cu12==12.6.4.1
+nvidia-cuda-cupti-cu12==12.6.80
+nvidia-cuda-nvrtc-cu12==12.6.77
+nvidia-cuda-runtime-cu12==12.6.77
+nvidia-cudnn-cu12==9.5.1.17
+nvidia-cufft-cu12==11.3.0.4
+nvidia-cufile-cu12==1.11.1.6
+nvidia-curand-cu12==10.3.7.77
+nvidia-cusolver-cu12==11.7.1.2
+nvidia-cusparse-cu12==12.5.4.2
+nvidia-cusparselt-cu12==0.6.3
+nvidia-nccl-cu12==2.26.2
+nvidia-nvjitlink-cu12==12.6.85
+nvidia-nvtx-cu12==12.6.77
+packaging==25.0
+pillow==11.2.1
+pydantic==2.11.5
+pydantic_core==2.33.2
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.3
+sentence-transformers==4.1.0
+setuptools==80.9.0
+sniffio==1.3.1
+starlette==0.46.2
+sympy==1.14.0
+threadpoolctl==3.6.0
+tokenizers==0.21.1
+torch==2.7.1
+tqdm==4.67.1
+transformers==4.52.4
+triton==3.3.1
+typing-inspection==0.4.1
+typing_extensions==4.14.0
+urllib3==2.4.0
+uvicorn==0.34.3