iamlemec
diff --git a/‎llama_cpp/llama.py
Copy file name to clipboardExpand all lines: llama_cpp/llama.py
+1-1Lines changed: 1 addition & 1 deletion b/‎llama_cpp/llama.py
Copy file name to clipboardExpand all lines: llama_cpp/llama.py
+1-1Lines changed: 1 addition & 1 deletion
diff --git a/‎llama_cpp/llama_cpp.py
Copy file name to clipboardExpand all lines: llama_cpp/llama_cpp.py
+16Lines changed: 16 additions & 0 deletions b/‎llama_cpp/llama_cpp.py
Copy file name to clipboardExpand all lines: llama_cpp/llama_cpp.py
+16Lines changed: 16 additions & 0 deletions
@@ -814,7 +814,7 @@ def decode_batch(n_seq: int):
 
             # store embeddings
             for i in range(n_seq):
-                embedding: List[float] = llama_cpp.llama_get_embeddings_ith(
+                embedding: List[float] = llama_cpp.llama_get_embeddings_seq(
                     self._ctx.ctx, i
                 )[:n_embd]
                 if normalize:
 
@@ -1803,6 +1803,22 @@ def llama_get_embeddings_ith(
     ...
 
 
+# // Get the embeddings for sequence seq_id
+# // shape: [n_embd] (1-dimensional)
+# LLAMA_API float * llama_get_embeddings_seq(struct llama_context * ctx, llama_seq_id seq_id);
+@ctypes_function(
+    "llama_get_embeddings_seq",
+    [llama_context_p_ctypes, ctypes.c_int32],
+    ctypes.POINTER(ctypes.c_float),
+)
+def llama_get_embeddings_seq(
+    ctx: llama_context_p, i: Union[ctypes.c_int32, int], /
+) -> CtypesArray[ctypes.c_float]:
+    """Get the embeddings for sequence seq_id
+    shape: [n_embd] (1-dimensional)"""
+    ...
+
+
 # // Get the embeddings for a sequence id
 # // Returns NULL if pooling_type is LLAMA_POOLING_TYPE_NONE
 # // shape: [n_embd] (1-dimensional)