Skip to content

feat(litellm): align embedding instrumentation with pending spec #2238

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

feat(litellm): align embedding instrumentation with pending spec #2238

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
be42c68
feat(embeddings): align embedding instrumentation with spec
codefromthecrypt Oct 11, 2025
b9dc097
cleanup
codefromthecrypt Oct 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
71 changes: 61 additions & 10 deletions ...eninference-instrumentation-litellm/src/openinference/instrumentation/litellm/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
import json
from enum import Enum
from functools import wraps
from typing import (
Expand Down Expand Up @@ -62,6 +61,9 @@
ToolCallAttributes,
)

# TODO: Update to use SpanAttributes.EMBEDDING_INVOCATION_PARAMETERS when released in semconv
_EMBEDDING_INVOCATION_PARAMETERS = "embedding.invocation_parameters"

# Skip capture
KEYS_TO_REDACT = ["api_key", "messages"]

Expand Down Expand Up @@ -269,7 +271,37 @@ def _instrument_func_type_embedding(span: trace_api.Span, kwargs: Dict[str, Any]
_set_span_attribute(
span, SpanAttributes.EMBEDDING_MODEL_NAME, kwargs.get("model", "unknown_model")
)
_set_span_attribute(span, EmbeddingAttributes.EMBEDDING_TEXT, str(kwargs.get("input")))

# Extract invocation parameters (exclude sensitive keys and input)
invocation_params = {
k: v for k, v in kwargs.items() if k not in KEYS_TO_REDACT and k != "input"
}
if invocation_params:
_set_span_attribute(
span, _EMBEDDING_INVOCATION_PARAMETERS, safe_json_dumps(invocation_params)
)

# Extract text from embedding input - only records text, not token IDs
embedding_input = kwargs.get("input")
if embedding_input is not None:
if isinstance(embedding_input, str):
# Single string input
_set_span_attribute(
span,
f"{SpanAttributes.EMBEDDING_EMBEDDINGS}.0.{EmbeddingAttributes.EMBEDDING_TEXT}",
embedding_input,
)
elif isinstance(embedding_input, list) and embedding_input:
# Check if it's a list of strings (not tokens)
if all(isinstance(item, str) for item in embedding_input):
# List of strings
for index, text in enumerate(embedding_input):
_set_span_attribute(
span,
f"{SpanAttributes.EMBEDDING_EMBEDDINGS}.{index}.{EmbeddingAttributes.EMBEDDING_TEXT}",
text,
)

_set_span_attribute(span, SpanAttributes.INPUT_VALUE, str(kwargs.get("input")))


Expand Down Expand Up @@ -301,13 +333,32 @@ def _finalize_span(span: trace_api.Span, result: Any) -> None:
)

elif isinstance(result, EmbeddingResponse):
# Extract model name from response (may differ from request model name)
if model_name := getattr(result, "model", None):
_set_span_attribute(span, SpanAttributes.EMBEDDING_MODEL_NAME, model_name)

if result_data := result.data:
first_embedding = result_data[0]
_set_span_attribute(
span,
EmbeddingAttributes.EMBEDDING_VECTOR,
json.dumps(first_embedding.get("embedding", [])),
)
# Extract embedding vectors directly (litellm uses enumeration, not explicit index)
for index, embedding_item in enumerate(result_data):
# LiteLLM returns dicts with 'embedding' key
raw_vector = (
embedding_item.get("embedding") if hasattr(embedding_item, "get") else None
)
if not raw_vector:
continue

vector = None
# Check if it's a list of floats
if isinstance(raw_vector, (list, tuple)) and raw_vector:
if all(isinstance(x, (int, float)) for x in raw_vector):
vector = tuple(raw_vector)

if vector:
_set_span_attribute(
span,
f"{SpanAttributes.EMBEDDING_EMBEDDINGS}.{index}.{EmbeddingAttributes.EMBEDDING_VECTOR}",
vector,
)
elif isinstance(result, ImageResponse):
if result.data and len(result.data) > 0:
if img_data := result.data[0]:
Expand Down Expand Up @@ -719,7 +770,7 @@ def _embedding_wrapper(self, *args: Any, **kwargs: Any) -> EmbeddingResponse:
if context_api.get_value(_SUPPRESS_INSTRUMENTATION_KEY):
return self.original_litellm_funcs["embedding"](*args, **kwargs) # type:ignore
with self._tracer.start_as_current_span(
name="embedding", attributes=dict(get_attributes_from_context())
name="CreateEmbeddings", attributes=dict(get_attributes_from_context())
) as span:
_instrument_func_type_embedding(span, kwargs)
result = self.original_litellm_funcs["embedding"](*args, **kwargs)
Expand All @@ -731,7 +782,7 @@ async def _aembedding_wrapper(self, *args: Any, **kwargs: Any) -> EmbeddingRespo
if context_api.get_value(_SUPPRESS_INSTRUMENTATION_KEY):
return self.original_litellm_funcs["aembedding"](*args, **kwargs) # type:ignore
with self._tracer.start_as_current_span(
name="aembedding", attributes=dict(get_attributes_from_context())
name="CreateEmbeddings", attributes=dict(get_attributes_from_context())
) as span:
_instrument_func_type_embedding(span, kwargs)
result = await self.original_litellm_funcs["aembedding"](*args, **kwargs)
Expand Down
21 changes: 21 additions & 0 deletions ...mentation/openinference-instrumentation-litellm/tests/cassettes/test_batch_embedding.yaml
View file
Open in desktop

Large diffs are not rendered by default.

19 changes: 19 additions & 0 deletions ...ce-instrumentation-litellm/tests/cassettes/test_batch_embedding_with_different_model.yaml
View file
Open in desktop

Large diffs are not rendered by default.

17 changes: 17 additions & 0 deletions ...n/openinference-instrumentation-litellm/tests/cassettes/test_single_string_embedding.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
interactions:
- request:
body: '{"input":"hello world","model":"text-embedding-ada-002","encoding_format":"base64"}'
headers: {}
method: POST
uri: https://api.openai.com/v1/embeddings
response:
body:
string: "{\n \"object\": \"list\",\n \"data\": [\n {\n \"object\":
\"embedding\",\n \"index\": 0,\n \"embedding\": \"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\"\n
\ }\n ],\n \"model\": \"text-embedding-ada-002-v2\",\n \"usage\": {\n
\ \"prompt_tokens\": 2,\n \"total_tokens\": 2\n }\n}\n"
headers: {}
status:
code: 200
message: OK
version: 1
Loading
Loading