feat(oss): port v3 pipeline with hybrid search, entity extraction, and additive scoring (#4805)

Co-authored-by: Soumil Rathi <soumilrathi@gmail.com>
Co-authored-by: Saket Aryan <saketaryan2002@gmail.com>
Co-authored-by: chaithanyak42 <chaithanya.kumar42a@gmail.com>
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>

mem0/embeddings/azure_openai.py

@@ -53,3 +53,20 @@ class AzureOpenAIEmbedding(EmbeddingBase):
         """
         text = text.replace("\n", " ")
         return self.client.embeddings.create(input=[text], model=self.config.model).data[0].embedding
+
+    def embed_batch(self, texts, memory_action="add"):
+        """Embed multiple texts in a single Azure OpenAI API call.
+
+        Automatically chunks into batches of 100 to stay within API limits.
+        """
+        MAX_BATCH = 100
+        texts = [text.replace("\n", " ") for text in texts]
+        all_embeddings = []
+        for i in range(0, len(texts), MAX_BATCH):
+            chunk = texts[i : i + MAX_BATCH]
+            response = self.client.embeddings.create(
+                input=chunk,
+                model=self.config.model,
+            )
+            all_embeddings.extend(item.embedding for item in sorted(response.data, key=lambda x: x.index))
+        return all_embeddings

mem0/embeddings/base.py

@@ -29,3 +29,19 @@ class EmbeddingBase(ABC):
             list: The embedding vector.
         """
         pass
+
+    def embed_batch(self, texts, memory_action="add"):
+        """Embed multiple texts. Override in subclasses for native batch support.
+
+        Default implementation calls embed() sequentially for each text.
+        Subclasses with native batch APIs (e.g., OpenAI) should override
+        this for better performance.
+
+        Args:
+            texts: List of text strings to embed.
+            memory_action: The action context ("add", "search", "update").
+
+        Returns:
+            List of embedding vectors (list of floats), one per input text.
+        """
+        return [self.embed(text, memory_action) for text in texts]

mem0/embeddings/openai.py

@@ -53,3 +53,24 @@ class OpenAIEmbedding(EmbeddingBase):
         if self._pass_dimensions_to_api:
             kwargs["dimensions"] = self.config.embedding_dims
         return self.client.embeddings.create(**kwargs).data[0].embedding
+
+    def embed_batch(self, texts, memory_action="add"):
+        """Embed multiple texts in a single OpenAI API call.
+
+        Automatically chunks into batches of 100 to stay within API limits.
+        """
+        MAX_BATCH = 100
+        texts = [text.replace("\n", " ") for text in texts]
+        all_embeddings = []
+        for i in range(0, len(texts), MAX_BATCH):
+            chunk = texts[i : i + MAX_BATCH]
+            kwargs = {
+                "input": chunk,
+                "model": self.config.model,
+                "encoding_format": "float",
+            }
+            if self._pass_dimensions_to_api:
+                kwargs["dimensions"] = self.config.embedding_dims
+            response = self.client.embeddings.create(**kwargs)
+            all_embeddings.extend(item.embedding for item in sorted(response.data, key=lambda x: x.index))
+        return all_embeddings