Langfuse v4 + Ollama: Tracing Local LLMs Without Mocks or Monkey-Patches
Langfuse v4 introduces a seamless way to trace local LLM interactions with Ollama by leveraging its compatibility with OpenAI's API format. By using a drop-in replacement for the OpenAI client, developers can automatically capture tracing data such as session IDs, user IDs, token counts, and full response streams without manual instrumentation. The integration simplifies observability for local LLMs while maintaining compatibility with OpenTelemetry standards.
- ▪Langfuse v4 uses a subclass of the OpenAI client to automatically trace Ollama chat completions at http://localhost:11434/v1.
- ▪Contextual metadata like session_id, user_id, and tags must be set using propagate_attributes() in Langfuse v4 due to its OpenTelemetry-based architecture.
- ▪The integration reconstructs streaming responses into a single trace, provided the entire stream iterator is consumed within the propagate_attributes context.
- ▪No custom OTLP exporters or monkey-patching are required, making the solution low-friction for local LLM observability.
- ▪Token usage is accurately captured from the response payload rather than estimated through middleware.
DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | DEV.to (Top) |
| Canonical URL | https://dev.to/jmolinasoler/langfuse-v4-ollama-tracing-local-llms-without-mocks-or-monkey-patches-478c |
| Publication time | Sat, 16 May 2026 09:28:21 +0000 |
| Retrieval time | 2026-05-16T09:40:18.070Z |
| Last seen | 2026-05-16T09:40:18.070Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | qfBF514-0ZEN |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3812537) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Julio Molina Soler Posted on May 16 Langfuse v4 + Ollama: Tracing Local LLMs Without Mocks or Monkey-Patches #llm #ai #python #observability Disclosure: I learn topics like this through LLM dialogue. The prompts are mine, the depth comes from the model, the verification comes back to me, and I publish the result so others don't have to start from zero.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
