🚀 Yesterday, Rogério Chaves took the stage at AI Builders (Join this community if you haven't yet) to speak about a more and more popular topic: Automated prompt engineering! 👏 Kudos to Rogerio for an incredible session 🌟 He showcased optimizing a RAG solution and visualized the results using the DSPy framework and visualizer. Interested in learning more about this topic and missed the session? Reach out to us via: https://lnkd.in/eN_PpebD and mention "auto-prompting" in the comments. #AI #DSPy #AutomatedPromptEngineering #Innovation
LangWatch
Softwareontwikkeling
Amsterdam, North Holland 561 volgers
Improve your LLM app with Monitoring & User analytics
Over ons
AI solutions are becoming fundamental to businesses of all sizes. Langwatch provides all-in-one tooling to improve and iterate on your current models, as well as mitigating risks such as data leakage, jailbreaking and hallucinations. To create AI with confidence, create it with Langwatch.
- Website
-
https://langwatch.ai/
Externe link voor LangWatch
- Branche
- Softwareontwikkeling
- Bedrijfsgrootte
- 2-10 medewerkers
- Hoofdkantoor
- Amsterdam, North Holland
- Type
- Particuliere onderneming
- Opgericht
- 2023
Locaties
-
Primair
Fred. Roeskestraat 115
Amsterdam, North Holland 1016, NL
Medewerkers van LangWatch
-
Richard Huth
Software Engineer | Ex-Founder | Kitesurfer
-
Manouk Draisma
📊 Monitor & improve the quality & safety of your (Gen)AI solutions and ship with confidence.
-
Rogério Chaves
Co-Founder @ LangWatch - Measure the quality and continuously improve your LLM apps
-
Yevhenii Budnyk
AI Developer and Entrepreneur
Updates
-
🚀 Exciting News for LLM Enthusiasts! 🚀 Have you started building your LLM-powered solutions with FlowiseAI (YC S23) We’re excited to share that LangWatch is now fully integrated into Flowise! 🌟 Build your perfect AI solution while we handle monitoring, quality checks, and provide full visibility into your user analytics. Say goodbye to the black-box and gain deeper insights into your AI's performance. #AI #LLM #genai #llmops #monitoring #qualitycontrol #UserInsights
Flowise v1.8.3 release 🎊 New models - Claude Sonnet 3.5 - Azure gpt-4o - Voyage-2 embeddings and reranker models Chat Embed - Agent reasoning steps - Tooltip display - Notification sound You can find the all the configurations: https://lnkd.in/ebQ3HrnQ 🔥 FireCrawl Web Scraper Crawl and convert any website into LLM-ready markdown or structured data in Flowise, thanks Mendable team for the integration! 🔭 LangWatch observability New observability tool in Flowise! Docs: https://lnkd.in/eAj77dXB 📚 Multi Query Retriever 1. Generate multiple queries for a given user question 2. For each query, retrieves a set of relevant documents 3. Takes the unique union across all queries for relevant documents This significantly enhances the final result due to the comprehensive answers from multiple perspectives! For more bugfixes and improvement details, check out the release page: https://lnkd.in/eTKvkJXh
-
Excited to share that LangWatch is at The AI Summit in London today and tomorrow! 🇬🇧 Visit us at the Dutch booth, "The Garden," where we’ll be joined by other amazing startups. Don't miss the opportunity to stop by and meet with us! Thanks to Rijksdienst voor Ondernemend Nederland (RVO) for the organisation.
-
-
"After many hours of manual prompt engineering we couldn't get the accuracy higher than 60%, DSPy took it to 80% for us in a matter of minutes." DSPy is the hot new framework on LLM community, which takes a different approach than what so far has been done for the past year: instead of having engineers manually trying to adjust prompt to improve results and do a *vibe-checking* on the outputs. That's why LangWatch implemented the DSPy Visualizer, which allows you to log your DSPy training sessions, track the performance, costs, compare runs and debug them in detail on the LangWatch platform. Read more here: https://lnkd.in/e_e8e_m4 Curious to try it out? Book a demo with us: https://lnkd.in/eN_PpebD #dspy #promptengineering #llms #genai
-
Preventing 'bullshit' output in LLM-powered applications is crucial for ensuring reliable and trustworthy AI interactions. Setting up the right quality evaluations is key to mitigating this issue. Here are some tips to get started: 1. Establish Baselines: Define clear baselines for what constitutes acceptable and unacceptable responses. This helps in identifying deviations more effectively. 2. Context Relevancy: Evaluate whether the AI’s responses are contextually relevant. This means checking if the information provided aligns with the query and context given. 3. Faithfulness: Ensure that the responses are faithful to the provided context and do not introduce information that cannot be inferred from it. 4. Use Custom Evaluations: Leverage custom evaluations tailored to your specific use case. Generic metrics often fall short, so customize your evaluations to focus on your application's unique requirements. Lastly, continuously monitor and review the product performance. By implementing these strategies, you can significantly reduce hallucinations and enhance the reliability of your LLM-powered application. Stop nonsense output before they start – set up the right evaluations today! Sign-up for a Expert Call with one of the specialists on this topic: https://lnkd.in/eN_PpebD or Check-out LangEvals: https://lnkd.in/e9FTb6aD
Request a demo
get.langwatch.ai
-
Our dev team is speedy 🏎️ 💨 as well tonight. Adding GPT4o to the new playground feauture to compare your models and use the best chosen model for your AI use case. Reach out if you want to learn more. https://lnkd.in/eN_PpebD
NEW GPT-4o VS LLAMA 3 SPEED TEST 🏎️💨 OpenAI just announced their new model GPT-4o with impressive capabilities, taking multimodal to a whole new level which definitively took the spotlight, but not only that, GPT-4o is smarter, cheaper and way faster And today we at LangWatch are releasing publicly our playground feature, and making GPT-4o immediately available on it, you can compare with other models, like the race against Llama 3 on Groq on the video below, it's impressive to watch! GPT-4o is also immediately available for all our LLM evaluators, meaning you can automatically make your LLM evaluators more powerful for half of the price per token! https://app.langwatch.ai
-
We would like to thank all our users & supporters as part of our journey building LangWatch. Check us out on ProductHunt, and support us with a little Upvote 🙂
Ready to get into action after my recent video posts? 😉 🤯 Our product LangWatch is LIVE on ProductHunt! Search for LangWatch or go to: https://lnkd.in/eXDH7Up5 and please share your feedback in the comments section. 🙏 💥 We believe it is a game changer for AI builders: With LangWatch, you ship AI products with confidence ✨ 1. No More blackbox - Powering decisions with insights 2. Mitigate safety risks, know where your AI product is hallucinating > Increase Quality 3. Safeguarding it against malicious practices like jailbreaking 🙏🏻 We would be thrilled if you'd have a look at our launch page and show us your support 💚 So much hard work from the team to get to today. We can't wait to see what you'll do with the tool. 🚀 Upwards and onwards
Product Hunt – The best new products in tech.
producthunt.com
-
Thanks Sonam Gupta for the great talk in your podcast about "Monitoring LLMs is Important" with our CTO, Rogério Chaves. We love your enthusiasm about this topic! 😊
Passionate Developer Advocate | Experienced Data Scientist | PhD Data Science | NLP | Machine Learning
Hallucinations, or weird behavior coming out of your LLM application? What do you do in this case? You build a monitoring layer at the end of your pipeline. How do you do it? Use a monitoring tool and LLM evaluation in your application. I had such questions answered by Rogério Chaves from LangWatch in our most recent podcast episode. Check out the highlights below: 🚀 Key Takeaways: - Rise in developer productivity using AI systems like copilots - Challenges like jailbreaking generative AI systems and the strong need for LLM monitoring tools to tackle such challenges - Different examples of jailbreaking user behavior - Importance of iterating over prompt engineering, and the rest of the development process without breaking the existing pipeline. That's not all! To learn more about monitoring LLMs, tune in to the full episode. [Link in comments] P.S.: Thank you Manouk Draisma for introducing us. P.S.S: Revamped the cover pic design :D Canva is awesome.
-
-
LangWatch heeft dit gerepost
After a successful beta period with the support of our amazing users and team, we are officially launching Langwatch.ai by the end of this month to more users and on Product Hunt. Want to get notified when? Hit ‘Notify me’ and check out our launch. https://lnkd.in/eNad795P With LangWatch, you ship AI products with confidence: Safeguard your AI 💂 We control your AI with our safety checks through guardrails that prevent jailbreaking, off-topic conversations, sensitive data leakage, and brand reputational damage. Analyze and improve 📊 Our real-time insights help you track user feedback, conversion, output quality, and knowledge base gaps. Ship with confidence 🛳️ 💁♀️ Test different models and prompts, improve existing and new datasets and ship new versions of your AI tool without breaking it. Ideal for AI builders. 2 more weeks to ship before going live…! Get notified here: https://lnkd.in/eNad795P
Coming soon: Launch your AI solutions with confidence | Product Hunt
producthunt.com
-
🚀
We are excited to share that LangWatch has been granted €150.000 funding from Rabobank through the Rabobank Innovation Fund program for startups. This funding will help LangWatch.ai to further develop the product and become the Quality & Analytics platform - helping companies build Generative AI solutions with confidence. 📊 Thanks, Rabobank, Wouter Stevens for your trust in us as a team and the product that we are building! with, Rogério Chaves #RIL #startup #innovation #funding