Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+embeded_data.json filter=lfs diff=lfs merge=lfs -text

embeded_data.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8208fd5ff051c60c23288fc096d1ee5449951d679b6b103edf8efd07dd7721
+size 95939294

get_similar_hadiths.py

@@ -0,0 +1,55 @@
+import pandas as pd
+import os
+import numpy as np
+from openai import OpenAI
+
+class HadithSearch:
+    def __init__(self, api_key):
+        self.client = OpenAI(api_key=api_key)
+        self.data = None
+
+    def _cosine_similarity(self, a, b):
+        return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
+
+    def _get_embedding(self, text, model="text-embedding-ada-002"):
+        try:
+            text = text.replace("\n", " ")
+        except Exception as e:
+            pass
+        text = "Ceci est le ressenti d'un musulman et nous cherchons les hadiths qui peuvent l'aider: " + text
+        return self.client.embeddings.create(input=text, model=model).data[0].embedding
+
+    def load_data_from_json(self, json_file):
+        self.data = pd.read_json(json_file)
+
+    def search_hadiths(self, user_input, num_hadiths=10):
+        if self.data is None:
+            raise ValueError("Data not loaded. Use load_data_from_json method to load data.")
+        
+        embedding_column_name = "embeddings"
+        try:
+            self.data[embedding_column_name] = self.data.embeddings.apply(lambda x: x["embeding"])
+        except Exception as e:
+            pass
+
+        embedding = self._get_embedding(user_input, model='text-embedding-ada-002')
+        self.data['similarity'] = self.data.embeddings.apply(lambda x: self._cosine_similarity(x, embedding))
+
+        results = self.data.sort_values('similarity', ascending=False).head(int(num_hadiths)).to_dict(orient="records")
+        formatted_results = self._format_results(results)
+        return formatted_results
+
+    def _format_results(self, results):
+        formatted_output = ""
+        for idx, result in enumerate(results, start=1):
+            similarity_percentage = str(round(result["similarity"] * 100, 2)) + "%"
+            book = result["book"]
+            chapter = result["chapter"]
+            content = result["content"]
+            display = (
+                f"## Hadith numéro {idx}: Pertinence par rapport à votre situation : {similarity_percentage}\n"
+                f"## Livre : {book}\n"
+                f"## Chapitre : {chapter}\n{content}\n\n------\n\n"
+            )
+            formatted_output += display
+        return formatted_output