Companies with LLM-based products (specifically Retrieval-Augmented Generation)deployed in production - how are you monitoring outputs for hallucinations? What's your process?
How are generative AI companies monitoring their systems in production?
1–10 of 18 posts
Re: How are generative AI companies monitoring their systems in production?
#2Also very interested in this question. We are looking at Truera for observability.
Re: How are generative AI companies monitoring their systems in production?
#3We are also looking for a solution for the same.. Currently evaluating LangSmith for the same.
Re: How are generative AI companies monitoring their systems in production?
#4Langkit is an option. WhyLabs has published a number of blog posts on this subject recently: https://whylabs.ai/blog/posts/monitoring-llm-performance-wit...
Re: How are generative AI companies monitoring their systems in production?
#5We struggled with this ourselves while building LLM-based products and then open-sourced our observability/monitoring tool [1]. Many use it to track RAG and agents in production, run custom evals on the production traces (focused on hallucination), and track how metrics are different across releases or customers. Feel free to dm if there is something specific you are looking to solve, happy to help.
Re: How are generative AI companies monitoring their systems in production?
#6I've been looking into this question for a bit. [1]
Here's my notes on evals --
Things to consider when comparing options:
1) “Types of metrics supported (only NLP metrics, model-graded evals, or both), level of customizability; supports component eval (i.e. single prompts) or pipeline evals (i.e. testing the entire pipeline, all the way from retrieval to post-processing)”
2) “+method of dataset & eval management (config vs UI), tracing to help debug failing evals”
3) “If you wanted to go deeper on evaluation, I'd probably also add:
What to evaluate for:
- Hallucination
- Safety
- Usefulness
- Tone / format (eg conciseness)
- Specific regressions
Tips:
- Model-graded evaluation is taking off
- Use GPT-4, GPT-3.5 is not good enough [for evals]
- Most big companies have some human oversight of the model-grading
- Conversational simulation is an emerging idea building on top of model-graded eval” - AI Startup Founder
---
Here are a few that people are using for evals at production scale:
* Honeyhive https://honeyhive.ai
* Gentrace https://gentrace.ai
* Humanloop https://humanloop.com
* Gantry https://www.gantry.io
I've done calls with the founders of three of those four, and I've talked with enterprise customers who've been evaluating a couple of those.
I see there's a few others mentioned in this thread (langfuse, truera, langkit/whylabs) that I haven't heard about from customers but also look promising. There's also langsmith which I do know is popular amongst enterprises (enterprises hear of langchain, see that they have a big enterprise-oriented offering) but I haven't talked with anyone who uses it.
Then for evals at prototyping scale there are various small tools and open source tools that I've collected here: https://llm-utils.org/List+of+tools+for+prompt+engineering
[1]: I'm working on an AI infra handbook. Email me, email in profile, if you can review/add comments to my draft. It's 23 pages long :x
Re: How are generative AI companies monitoring their systems in production?
#7I've been looking into this question for a bit. [1] Here's my notes on evals -- Things to consider when comparing options: 1) “Types of metrics supported (only NLP metrics, model-graded evals, or both), level of customizability; supports component eval (i.e. single prompts) or pipeline evals (i.e. testing the entire pipeline, all the way from retrieval to post-processing)” 2) “+method of dataset & eval management (co…
Then there's also monitoring. My notes from the monitoring section are below:
When needed: “it goes hand-in-hand with eval, as you need to be able to turn bad prod generations into failing eval cases for eng to make pass”
Considerations:
1) “Ability to monitor custom metrics (ROUGE [1], Coherence, etc.) and slice-and-dice data - customizability; non-intrusive logging vs proxies, VPC (enterprise-readiness). Plenty of tools w/ basic cost, latency monitoring; very few w/ enterprise-grade customizability, anomaly detection, etc.”
2) “+agent/pipeline tracing, ability to re-purpose data for fine tuning, connection to user feedback, man-in-the-middle approach (proxy) vs SDK integration (we believe SDK is superior so your monitoring vendor can go down without taking down your LLM feature)”
Companies for LLM monitoring: Helicone, Honeyhive, Gentrace, Humanloop, Langsmith, Pezzo
Re: How are generative AI companies monitoring their systems in production?
#8I've been looking into this question for a bit. [1] Here's my notes on evals -- Things to consider when comparing options: 1) “Types of metrics supported (only NLP metrics, model-graded evals, or both), level of customizability; supports component eval (i.e. single prompts) or pipeline evals (i.e. testing the entire pipeline, all the way from retrieval to post-processing)” 2) “+method of dataset & eval management (co…
Do you have any links to conversational simulation?
Re: How are generative AI companies monitoring their systems in production?
#9There are quite a few LLM monitoring tools in the market. But for monitoring (or evaluating) RAG systems, I found Ragas to be the most helpful: https://blog.langchain.dev/evaluating-rag-pipelines-with-rag...
Re: How are generative AI companies monitoring their systems in production?
#10I've been looking into this question for a bit. [1] Here's my notes on evals -- Things to consider when comparing options: 1) “Types of metrics supported (only NLP metrics, model-graded evals, or both), level of customizability; supports component eval (i.e. single prompts) or pipeline evals (i.e. testing the entire pipeline, all the way from retrieval to post-processing)” 2) “+method of dataset & eval management (co…
Do you have any links to conversational simulation?
Here's the note I have on that: “For chatbot interfaces, emerging approach is to have another agent simulating the user (as opposed to a more classic approach based on token prediction probs on chat transcripts, what I think you're referencing). Then still use a model for grading. Only place I've seen this so far: https://github.com/Forethought-Technologies/AutoChain/blob/m... ” - AI Startup Founder