From 4d95016f35c4ff7acd75a9db49750d8a93763e9f Mon Sep 17 00:00:00 2001
From: as992949791 <as992949791@gmail.com>
Date: Fri, 30 Oct 2026 12:37:40 +0800
Subject: [PATCH 1/2] fix(openai): count base64 embedding vector dimensions

Generated with OpenAI Codex.
---
 langfuse/openai.py        |  8 +++++++-
 tests/unit/test_openai.py | 40 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/langfuse/openai.py b/langfuse/openai.py
index 32637569b..692ca42e6 100644
--- a/langfuse/openai.py
+++ b/langfuse/openai.py
@@ -23,6 +23,7 @@
 See docs for more details: https://langfuse.com/docs/integrations/openai
 """
 
+import base64
 import json
 import os
 import types
@@ -963,8 +964,13 @@ def _get_langfuse_data_from_default_response(
                 if hasattr(first_embedding, "embedding")
                 else first_embedding.get("embedding", [])
             )
+            if isinstance(embedding_vector, str):
+                # Base64 embeddings contain one float32 per dimension.
+                dimensions = len(base64.b64decode(embedding_vector)) // 4
+            else:
+                dimensions = len(embedding_vector) if embedding_vector else 0
             completion = {
-                "dimensions": len(embedding_vector) if embedding_vector else 0,
+                "dimensions": dimensions,
                 "count": len(data),
             }
 
diff --git a/tests/unit/test_openai.py b/tests/unit/test_openai.py
index a2a4f7f4f..2bde0e237 100644
--- a/tests/unit/test_openai.py
+++ b/tests/unit/test_openai.py
@@ -3,6 +3,7 @@
 from types import SimpleNamespace
 from unittest.mock import patch
 
+import httpx
 import pytest
 from openai.types.chat import ChatCompletion
 from openai.types.responses import ParsedResponseOutputMessage, ParsedResponseOutputText
@@ -1015,6 +1016,45 @@ def test_embedding_exports_dimensions_and_count(
     }
 
 
+@pytest.mark.parametrize("dimensions", [1, 2, 3])
+def test_base64_embedding_exports_vector_dimensions(
+    langfuse_memory_client, get_span, json_attr, dimensions
+):
+    encoded_embedding = base64.b64encode(bytes(4 * dimensions)).decode()
+
+    def respond(request):
+        return httpx.Response(
+            200,
+            json={
+                "model": "text-embedding-3-small",
+                "object": "list",
+                "data": [
+                    {"index": 0, "object": "embedding", "embedding": encoded_embedding}
+                ],
+                "usage": {"prompt_tokens": 2, "total_tokens": 2},
+            },
+        )
+
+    with lf_openai.OpenAI(
+        api_key="test",
+        http_client=httpx.Client(transport=httpx.MockTransport(respond)),
+    ) as openai_client:
+        result = openai_client.embeddings.create(
+            name="unit-openai-base64-embedding",
+            model="text-embedding-3-small",
+            input="hello world",
+            encoding_format="base64",
+        )
+
+    assert result.data[0].embedding == encoded_embedding
+    langfuse_memory_client.flush()
+    span = get_span("unit-openai-base64-embedding")
+    assert json_attr(span, LangfuseOtelSpanAttributes.OBSERVATION_OUTPUT) == {
+        "dimensions": dimensions,
+        "count": 1,
+    }
+
+
 def _make_chat_response(**extra_response_fields):
     return SimpleNamespace(
         model="gpt-4o-mini",

From 4f61fd00ca9c5915470b4c04b83dc0a46163a13d Mon Sep 17 00:00:00 2001
From: as992949791 <as992949791@gmail.com>
Date: Fri, 30 Oct 2026 12:42:24 +0800
Subject: [PATCH 2/2] fix(openai): preserve malformed embedding response
 passthrough

Generated with OpenAI Codex.
---
 langfuse/openai.py        |  8 ++++++--
 tests/unit/test_openai.py | 14 +++++++++++---
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/langfuse/openai.py b/langfuse/openai.py
index 692ca42e6..0b77e1729 100644
--- a/langfuse/openai.py
+++ b/langfuse/openai.py
@@ -24,6 +24,7 @@
 """
 
 import base64
+import binascii
 import json
 import os
 import types
@@ -965,8 +966,11 @@ def _get_langfuse_data_from_default_response(
                 else first_embedding.get("embedding", [])
             )
             if isinstance(embedding_vector, str):
-                # Base64 embeddings contain one float32 per dimension.
-                dimensions = len(base64.b64decode(embedding_vector)) // 4
+                try:
+                    # Base64 embeddings contain one float32 per dimension.
+                    dimensions = len(base64.b64decode(embedding_vector)) // 4
+                except (binascii.Error, ValueError):
+                    dimensions = len(embedding_vector)
             else:
                 dimensions = len(embedding_vector) if embedding_vector else 0
             completion = {
diff --git a/tests/unit/test_openai.py b/tests/unit/test_openai.py
index 2bde0e237..ae1bc1c58 100644
--- a/tests/unit/test_openai.py
+++ b/tests/unit/test_openai.py
@@ -1016,11 +1016,19 @@ def test_embedding_exports_dimensions_and_count(
     }
 
 
-@pytest.mark.parametrize("dimensions", [1, 2, 3])
+@pytest.mark.parametrize(
+    "encoded_embedding, dimensions",
+    [
+        ("AAAAAA==", 1),
+        ("AAAAAAAAAAA=", 2),
+        ("AAAAAAAAAAAAAAAA", 3),
+        pytest.param("!invalid!", 9, id="invalid-base64"),
+        pytest.param("\u2603", 1, id="non-ascii"),
+    ],
+)
 def test_base64_embedding_exports_vector_dimensions(
-    langfuse_memory_client, get_span, json_attr, dimensions
+    langfuse_memory_client, get_span, json_attr, encoded_embedding, dimensions
 ):
-    encoded_embedding = base64.b64encode(bytes(4 * dimensions)).decode()
 
     def respond(request):
         return httpx.Response(