Update app.py

app.py

@@ -2,95 +2,46 @@ import numpy as np
 import gradio as gr
 from sentence_transformers import SentenceTransformer, util
 
-# Available models
-model_dict = {
-    "AviLaBSE" :"sartifyllc/AviLaBSE",
-    "MultiLinguSwahili-serengeti-E250-nli-matryoshka": "sartifyllc/MultiLinguSwahili-serengeti-E250-nli-matryoshka",
-    "MultiLinguSwahili-bert-base-sw-cased-nli-matryoshka": "Mollel/MultiLinguSwahili-bert-base-sw-cased-nli-matryoshka",
-    "swahili-paraphrase-multilingual-mpnet-base-v2-nli-matryoshka": "sartifyllc/swahili-paraphrase-multilingual-mpnet-base-v2-nli-matryoshka",
-    "bge-base-swahili-matryoshka":"sartifyllc/bge-base-swahili-matryoshka",
-    "MultiLinguSwahili-bge-small-en-v1.5-nli-matryoshka": "sartifyllc/MultiLinguSwahili-bge-small-en-v1.5-nli-matryoshka",
-}
-
 # Function to load the selected model
 def load_model(model_name):
-    return SentenceTransformer(model_dict[model_name])
+    return SentenceTransformer(model_name)
 
 # Function to compute similarity and classify relationship
-def predict(model_name, mode, sentence1, sentence2=None, sentence3=None, sentence4=None, dimension="64"):
+def predict(model_name, original_sentence_input, *sentences_to_compare):
     model = load_model(model_name)
-    dimension = int(dimension)
     result = {
-        "Selected Dimension": dimension,
-        "Input Sentences": {
-            "Sentence 1": sentence1,
-            "Sentence 2": sentence2,
-            "Sentence 3": sentence3,
-            "Sentence 4": sentence4
-        },
+        "Model Name": model_name,
+        "Original Sentence": original_sentence_input,
+        "Sentences to Compare": sentences_to_compare,
         "Similarity Scores": {}
     }
     
-    if mode == "Compare one to three":
-        if sentence2 is None or sentence3 is None or sentence4 is None:
-            return "Please provide three sentences for comparison.", {}
-        sentences = [sentence1, sentence2, sentence3, sentence4]
-    else:
-        if sentence2 is None:
-            return "Please provide the second sentence for comparison.", {}
-        sentences = [sentence1, sentence2]
-    
-    embeddings = model.encode(sentences)
-    embeddings = embeddings[..., :dimension]
-    
-    if mode == "Compare one to three":
-        similarities = util.cos_sim(embeddings[0], embeddings[1:])
-        similarity_scores = {f"Sentence {i+2}": float(similarities[0, i]) for i in range(3)}
-        result["Similarity Scores"] = similarity_scores
-    else:
-        similarity_score = util.cos_sim(embeddings[0], embeddings[1])
-        similarity_scores = {"Similarity Score": float(similarity_score)}
-        result["Similarity Scores"] = similarity_scores
-    
-    # Word-level similarity
-    if mode == "Compare two sentences" and sentence2 is not None:
-        words1 = sentence1.split()
-        words2 = sentence2.split()
-        word_pairs = [(w1, w2) for w1 in words1 for w2 in words2]
-        word_embeddings1 = model.encode(words1)[..., :dimension]
-        word_embeddings2 = model.encode(words2)[..., :dimension]
-        word_similarities = {
-            f"{w1} - {w2}": float(util.cos_sim(we1, we2))
-            for (w1, we1) in zip(words1, word_embeddings1)
-            for (w2, we2) in zip(words2, word_embeddings2)
-        }
-        result["Word-level Similarities"] = word_similarities
+    if original_sentence_input and sentences_to_compare:
+        sentences = [original_sentence_input] + list(sentences_to_compare)
+        embeddings = model.encode(sentences)
+        original_embedding = embeddings[0]
+
+        for i, sentence in enumerate(sentences_to_compare, start=1):
+            similarity_score = util.pytorch_cos_sim(original_embedding, embeddings[i]).item()
+            result["Similarity Scores"][f"Sentence {i}"] = similarity_score
     
     return result
 
 # Define inputs and outputs for Gradio interface
-model_name = "AviLABASE", label="Model")
-sentence1_input = gr.Textbox(lines=2, placeholder="Enter the first sentence here...", label="Sentence 1")
-sentence2_input = gr.Textbox(lines=2, placeholder="Enter the second sentence here...", label="Sentence 2 (or first of three for mode)")
-sentence3_input = gr.Textbox(lines=2, placeholder="Enter the third sentence here...", label="Sentence 3")
-sentence4_input = gr.Textbox(lines=2, placeholder="Enter the fourth sentence here...", label="Sentence 4")
+model_name = gr.Textbox(value="sartifyllc/African-Cross-Lingua-Embeddings-Model", label="Model Name")
+original_sentence_input = gr.Textbox(lines=2, placeholder="Enter the original sentence here...", label="Original Sentence")
+sentence_to_compare_inputs = gr.Textbox(lines=2, placeholder="Enter the sentence you want to compare...", label="Sentence to Compare", elem_id="sentence_to_compare")
 
-inputs = [model_name, sentence1_input, sentence2_input, sentence3_input, sentence4_input]
+inputs = [model_name, original_sentence_input, sentence_to_compare_inputs]
 outputs = gr.JSON(label="Detailed Similarity Scores")
 
-examples = [
-    ["MultiLinguSwahili-serengeti-E250-nli-matryoshka", "Compare one to three", "Mtoto mdogo anaruka mikononi mwa mwanamke aliyevalia suti nyeusi ya kuogelea akiwa kwenye dimbwi.", "Mtoto akiruka mikononi mwa mwanamke aliyevalia suti ya kuogelea kwenye dimbwi.", "Mama na binti wakinunua viatu.", "Mtu anashindana katika mashindano ya mbio.", "64"],
-    ["MultiLinguSwahili-serengeti-E250-nli-matryoshka", "Compare two sentences", "Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi nyuma.", "tai huruka", None, None, "64"]
-]
-
 # Create Gradio interface
 gr.Interface(
     fn=predict,
-    title="Swahili Sentence Similarity with Matryoshka Model",
-    description="Compute the semantic similarity between Swahili sentences using various SentenceTransformer models.",
+    title="African Cross-Lingua Embeddings Model's Demo",
+    description="Compute the semantic similarity across various sentences among any African Languages using African-Cross-Lingua-Embeddings-Model.",
     inputs=inputs,
-    examples=examples,
     outputs=outputs,
     cache_examples=False,
-    article="Author: Michael Mollel. Model from Hugging Face Hub (sartify.com): [Swahili-Nli-Matryoshka](https://huggingface.co/sartifyllc/MultiLinguSwahili-serengeti-E250-nli-matryoshka)",
+    allow_flagging="never"
 ).launch(debug=True, share=True)