Duplicate from ijktech/matcher

Co-authored-by: James Kelly <[email protected]>

.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

README.md

@@ -0,0 +1,15 @@
+---
+title: Matcher
+emoji: 🏢
+colorFrom: green
+colorTo: gray
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+license: mit
+python_version: 3.10.8
+duplicated_from: ijktech/matcher
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,61 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModel
+import torch
+import torch.nn.functional as F
+
+
+# Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0]  # First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+class Matcher:
+
+    def __init__(self):
+        self.tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
+        self.model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
+
+    def _encoder(self, text: list[str]):
+        encoded_input = self.tokenizer(text, padding=True, truncation=True, return_tensors='pt')
+        with torch.no_grad():
+            model_output = self.model(**encoded_input)
+        sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+        sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
+        return sentence_embeddings
+
+    def __call__(self, textA: list[str], textB: list[str]):
+        embeddings_a = self._encoder(textA)
+        embeddings_b = self._encoder(textB)
+        sim = embeddings_a @ embeddings_b.T
+        match_inds = torch.argmax(sim, dim=1)
+        match_conf = torch.max(sim, dim=1).values
+        return match_inds.tolist(), match_conf.tolist()
+
+
+def run_match(source_text, destination_text):
+    matcher = Matcher()
+    sources = source_text.split("\n")
+    destinations = destination_text.split("\n")
+    match_inds, match_conf = matcher(sources, destinations)
+    matches = [f"{sources[i]} -> {destinations[match_inds[i]]} ({match_conf[i]:.2f})" for i in
+               range(len(sources))]
+    return "\n".join(matches)
+
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            source_text = gr.Textbox(lines=10, label="Query Text", name="source_text",
+                                     default="diavola with extra chillies\nseafood\nmargherita")
+        with gr.Column():
+            dest_text = gr.Textbox(lines=10, label="Target Text", name="destination_text",
+                                   default="cheese pizza\nhot and spicy pizza\ntuna, prawn and onion pizza")
+        with gr.Column():
+            matches = gr.Textbox(lines=10, label="Matches", name="matches")
+    with gr.Row():
+        match_btn = gr.Button(label="Match", name="run")
+        match_btn.click(fn=run_match, inputs=[source_text, dest_text], outputs=matches)
+
+    demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+torch==2.0.0
+transformers==4.25.1