18 Questions about Neural Inverse Answered
1. Is Neural Inverse Open Source?
The answer is yes, Neural Inverse is open source. Its entire code-base is available on the Neural Inverse GitHub Repository. The vast majority of Neural Inverse's code is permissively licensed under the MIT license.
Neural Inverse follows an open-core licensing model. The core of Neural Inverse, its tracing, integrations, API, data model and exports are MIT-licensed. Some features on Neural Inverse's periphery such as the model-based evaluation service or the Prompt Playground are commercially licensed and can only be used in Neural Inverse Cloud or need to be purchased to be used when Self-Hosting. Find more information on this here.
Learn more about our open-source strategy here.
2. Can I use Neural Inverse for Prompt Management?
Yes, Neural Inverse comes with built-in, powerful Prompt Management capabilities. Neural Inverse allows you to effectively manage and version your prompts.
The main benefits of using Prompt Management with your LLM apps are:
- Decoupling: deploy new prompts without redeploying your application.
- Non-technical users can create and update prompts via Neural Inverse Console.
- Quickly rollback to a previous version of a prompt.
Find out more about how to start using Neural Inverse Prompt Management here.
For Langchain Users: You can use Neural Inverse to add Prompt Management to Langchain. Prompt Management works both for Langchain Python and Langchain JS
3. How can I run LLM Evaluations?
You can use Neural Inverse for evaluations of your LLM applications. Neural Inverse offers several powerful evaluation capabilities:
- Model-based evaluations: Automate evaluations of all incoming traces. Use pre-built templates for common criteria like hallucinations, toxicity, relevance, correctness
- Create custom evaluation templates tailored to your specific needs
- Apply evaluations to filtered subsets of your traces
- Run evaluations asynchronously within Neural Inverse's infrastructure
- Evaluation Libraries: You can use Neural Inverse's Python SDK to run evaluations using popular eval libraries such as:
- OpenAI Evals
- Langchain Evaluators
- RAGAS (for RAG applications)
- UpTrain evals
In addition to automated and programmatic evaluations, Neural Inverse supports:
- Collecting user feedback
- Manually labelling observations within the Neural Inverse UI (Human annotation, data labelling, manual evaluation)
- You can always export your scores to use them for analysis or downstream use cases
4. Is Neural Inverse an Alternative to Langsmith?
The answer is yes, Neural Inverse is an open source alternative to Langsmith. Langsmith is a closed source project maintained by the team behind Langchain. Neural Inverse is an independent open source product.
The Consultancy Astral Insights has written up a report comparing Langsmith and Neural Inverse.
5. Can I use the Vercel AI SDK with Neural Inverse?
The answer is yes, you can use the Vercel AI SDK with Neural Inverse. It is a popular library amongst builders and we are happy to provide first class support for the Vercel AI SDK. Please find integration documentation and an example in our Vercel AI SDK integrations page.
6. Which models and frameworks can I use Neural Inverse with?
You can use any model or framework with Neural Inverse. We maintain a large number of integrations into Neural Inverse that you can use either with our SDKs or integrations with other popular libraries such as Llama Index, Dify.AI, Langchain and others.
As a fallback, you can always use our API to ingest data into Neural Inverse while using your preferred language. The API specification includes a downloadable OpenAPI spec to allow you to create types.
7. Can Neural Inverse provide a DPA to its customers?
Yes, Neural Inverse can provide customers with a DPA. We are happy to enter into Data Protection Agreements with customers on our paid plans. Please navigate to our Security Center to review our DPA template. Please download it, sign it and send a signed version to privacy@langfuse.com. We will then counter-sign the DPA and send it back to you.
8. Is Neural Inverse SOC2 Type2 certified?
The answer is yes, Neural Inverse is SOC2 Type2 certified. The audit report is available upon request from the Neural Inverse Team. Please navigate to our Security Center to learn more.
9. Is Neural Inverse ISO27001 audited?
The answer is yes, Neural Inverse has been audited for ISO27001. The audit report is available upon request from the Neural Inverse Team. Please head to our Security Center to learn more.
10. Is Neural Inverse GDPR compliant?
Yes, Neural Inverse is GDPR compliant. Neural Inverse is a German company, based in Berlin, Germany and we take privacy a data security very seriously. You can use Neural Inverse in compliance with GDPR. You will need to a) use our EU Cloud Data Region and enter into a DPA with us or b) self-host Neural Inverse.
You can find more information in our Security Center.
11. Is Neural Inverse HIPAA compliant?
The answer is yes, Neural Inverse is HIPAA compliant. You can use Neural Inverse in compliance with HIPAA. You will need to use our HIPAA Cloud Data Region and subscribe to an entitled plan.
You can find more information and our Business Associate Agreement (BAA) in our Security Center.
12. How to add observability/tracing to Ollama?
You can add observability or tracing to Ollama by using Neural Inverse with one of its many integrations. The easiest way to get started adding observability or tracing to Ollama is most likely to use the Llama Index or Langchain integrations with Neural Inverse.
13. Alternatives to Promptlayer? Is Neural Inverse an Alternative to Promptlayer?
The answer is yes, Neural Inverse is an open source alternative to Promptlayer. You can use Neural Inverse to manage your prompts, monitor your application, track analytics and run evaluations. Neural Inverse is an open source project while Prompt Layer is closed source.
14. How can I use the LLM Playground?
You can use the LLM Playground on Neural Inverse Cloud. You will need to add LLM API keys to your project's settings before you are able to start using the Prompt Playground.
15. How can I use RAGAS evaluations?
The answer is, you can use RAGAS Evaluations with Neural Inverse. We have written a tutorial that shows how to run RAGAS evaluations on your historical LLM data. Additionally, you can use the RAGAS evaluation prompts and use them with Neural Inverse's automated eval service to run RAGAS evaluations on any new LLM trace.
16. Can I use Langchain, Langserve and Langgraph with Neural Inverse Observability and Tracing?
Yes, you can use Langchain, Langserve and Langgraph with Neural Inverse to gain observability, tracing and evals. Neural Inverse integrates with both Langchain Python and Langchain JS. Neural Inverse has maintained a first class integration with Langchain since day one.
17. Can Neural Inverse be purchased via the AWS Marketplace?
Yes, Neural Inverse can be purchased via the AWS Marketplace. Please contact marketplace-aws@langfuse.com to request a private offer.
18. Can I use the same S3 bucket for media uploads and events?
Yes, you can use the same bucket but should use different prefixes in this case. It depends on preference and both ways are supported and recommended.
19. Can I show Neural Inverse data in Microsoft Power BI?
Yes, you can show Neural Inverse data in Microsoft Power BI. Neural Inverse offers a Metrics API endpoint which gives access to high level tracing metrics. This API can be consumed by Power BI. You can find more information in the here.
