support
self-host-support
get-support
feedback
feature-suggestion
self-host-discussion
announcements-releases
Pivot table of experiments results
Does Langfuse require being run in a Node environment?
Filter LangChain tool calls in dashboard
Get trace by metadata key
Langfuse batch outputs missing
langchain
batch calls. They either don't appear for any of the items in the batch, or only for the last one.
I have created an issue here: https://github.com/langfuse/langfuse/issues/2940
Appreciate any help on that!...Login problem
Summary evaluators. f1 score
Traces take too long to show up
Is it possible to score a full dataset run?
Is it possible to have a traces between different AWS Lambdas?
Structured Outputs OpenAI
Warning issue when disabled
Issue with prompt search
Extracting scores from traces ?
Is it possible to end a trace?
User feedback
custom generation langchain runnable lambda
_generate
method from ChatFireworks
(to be able to set the n
parameter) as follows:
RunnableLambda(lambda _messages: model._generate(_messages, **kwargs))
RunnableLambda(lambda _messages: model._generate(_messages, **kwargs))
LangChain+Ollama+Langfuse Not Recording Token Usage
ChatOllama
from LangChain to send LLM requests to local Ollama server. I am also integrating LangFuse with LangChain to trace the requests. The generation requests are being successfully traced, including the input and output of the model. However, the token usage is always 0. I attached a screenshot of one trace showing zero token usage.
I checked the output of LangChain's invoke method and the usage data is in the response. It's accessible via response.usage_metadata["input_tokens"]
and response.usage_metadata["output_tokens"]
.
I also tried langfuse_context.update_current_observation(usage={"input": response.usage_metadata["input_tokens"], "unit": "TOKENS"})
but it still shows zero....null value traces
Self-hosted models via API