Use Orq.ai as the model control layer for LangChain. Route LLM calls through one OpenAI‑compatible endpoint, capture traces, monitor cost, and manage fallback behavior without rebuilding your chains, agents, tools, or RAG pipelines.
What is LangChain?
LangChain is a Python and JS framework for building LLM‑powered applications with chains, agents, tools, and RAG, often paired with LangSmith for observability. It helps teams focus on workflow composition instead of manually wiring every tool, model, and vector store.
Why use Orq with LangChain
Trace chain and agent behavior end to end
Trace LangChain runs end to end, including prompts, tool calls, intermediate steps, model responses, and errors in one place. You get clearer visibility into how each chain or agent behaved, without stitching together logs across multiple services.
Model flexibility without rewiring chains
Test new models, add alternative providers, or assign different model tiers to different chains and agents from Orq.ai, while keeping your LangChain logic stable. Your ChatOpenAI, ChatAnthropic, or other LLM classes still “think” they are talking to a standard client; Orq handles which underlying model is called.
Evaluate real production runs
Use real LangChain traces like inputs, outputs, tool decisions, and errors to build datasets, compare prompt or model changes, and move from subjective tuning to measurable quality checks. Failed or slow runs can be turned into eval inputs before you roll out changes.
Control spend and access centrally
Track token usage and spend per chain, agent, team, and workflow so you can see which routes drive cost. Add budgets, rate limits, and approved‑model lists at the Orq platform layer instead of enforcing governance separately inside each LangChain project.
How the integration works
Step 1
Point LangChain’s LLMs at Orq.ai’s router
Use Orq’s OpenAI‑compatible base URL and key in your LangChain LLM clients (for example ChatOpenAI) or model slugs like openai:gpt-5-mini in LangGraph examples. This gives Orq the context it needs to apply routing rules, capture usage, and enforce fallback behavior.orq+1
Step 2
Enable tracing from LangChain to Orq
Set OpenTelemetry and LangSmith‑OTEL environment variables so LangChain/LangGraph traces are exported to Orq’s OTLP endpoint. LangChain continues to send data about chain and agent execution, and Orq records LLM interactions, latency, and cost metrics, so you can see both workflow‑level and model‑level traces.
Step 3
Define routes, fallbacks, and policies in Orq
Create routes for key LangChain workflows (for example RAG chains, ReAct agents, or multi‑tool orchestrators) and assign them model tiers, fallback chains, and region/data policies. LangChain sends LLM requests to the configured Orq routes, and Orq applies routing before invoking OpenAI, Gemini, Claude, or other models.
Step 4
Monitor, evaluate, and tune
Once connected, use Orq’s dashboards to watch latency, errors, and cost for LangChain/LangGraph apps, and run evals or experiments on their traces. You can adjust routes, models, or prompt configurations centrally where supported, while LangChain continues to handle chains, agents, tools, and memory.
Use Cases
Multi‑agent products with real observability
Trace which LangChain agent, tool, and model contributed to a failed workflow or unexpected outcome, combining LangSmith or other observability views with Orq’s router‑level traces.
Cost‑aware internal tools
Route routine steps like simple QA or summarization to lower‑cost models while keeping complex planning, multi‑tool agents, or enterprise RAG on your strongest routes configured in Orq.
Eval‑driven agent improvements
Reuse failed conversations, chain outputs, and tool decision logs as eval inputs before shipping prompt, tool, or model changes, turning production telemetry into a continuous improvement loop.
Safer experimentation across providers
Test a new model or provider on a small share of LangChain traffic, then promote or roll back based on traces and evals, instead of editing each agent or LLM config by hand.
FAQ
Do I have to change my LangChain code to use Orq.ai?
In many cases, you can repoint your ChatOpenAI (or similar) LLM client to Orq’s router (base URL, API key, and model name) and enable OTEL export to Orq, keeping chains and agents the same. Tools, vector stores, and other components stay in LangChain.
Does Orq.ai replace LangChain’s own runtime or framework?
No. LangChain and LangGraph remain your framework for agents and chains, and you can keep using LangSmith for deep trace analysis. Orq.ai sits alongside them as the control plane for models, multi‑provider routing, cost tracking, and additional evaluation.docs. You still design and run agents and chains in LangChain, but you use Orq to see what they cost, which models they should call, and how LLM behavior compares across providers under the same workflow.
Can I keep using my existing LLM providers with LangChain if I move to Orq.ai?
Yes. You can bring your existing provider keys (OpenAI, Anthropic, Google, etc.) into Orq.ai and route LangChain traffic through them, alongside any new models you add later. That way you centralize access, routing, and tracking without losing your current LangChain integrations. Bring production controls to LangChain apps
