arize-phoenix
@ArizePhoenix
Followers
977
Following
269
Media
64
Statuses
352
AI Observability and Evaluation
Notebook or Container
Joined February 2023
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Supreme Court
• 1158410 Tweets
SCOTUS
• 736416 Tweets
Portugal
• 469629 Tweets
Diogo Costa
• 269015 Tweets
Corinthians
• 139417 Tweets
Panamá
• 117726 Tweets
seokjin
• 110304 Tweets
Uruguay
• 108222 Tweets
JIN AT PARIS OLYMPICS
• 107701 Tweets
TORCHBEARER JIN
• 92613 Tweets
#WWERaw
• 89765 Tweets
Estados Unidos
• 86646 Tweets
PRIDE OF KOREA JIN
• 79402 Tweets
Bolivia
• 68464 Tweets
#CopaAmerica
• 50204 Tweets
オスカル
• 46652 Tweets
CLAMP
• 46441 Tweets
Veiga
• 40857 Tweets
CONMEBOL
• 34102 Tweets
#นุนิว3จุด3ทั้งซ่าทั้งแซ่บ
• 30367 Tweets
#USMNT
• 29066 Tweets
Wesley
• 25398 Tweets
Berhalter
• 23469 Tweets
Dakota
• 22626 Tweets
CONCACAF
• 22557 Tweets
ベルばら
• 19982 Tweets
ニコニコ超開示
• 17735 Tweets
Category 5
• 16600 Tweets
レイアース
• 15461 Tweets
Ugarte
• 11038 Tweets
Zoey
• 11024 Tweets
Pinned Tweet
If you are building an LLM application that uses RAG , poor retrieval can be detrimental to its UX. Phoenix now supports passing in your knowledge base as a corpus dataset so that you can inspect how your retrieval system is querying for relevant documents from your vector store.
6
54
327
Phoenix now supports DSPy! 🎉
With DSPy, you can declare the architecture of your LLM app and automatically generate prompts and fine-tune models to optimize for your specific task.
Try out the notebook:
@lateinteraction
#LLMs
#AI
5
35
123
Webinar with
@llama_index
!
@jerryjliu0
shows us the critical components across the data lifecycle to power RAG: ingest, index, query 🪄
And with the new OpenInferenceCallback, you can easily troubleshoot the search and retrieval with
@ArizePhoenix
! 🔮
1
7
55
Phoenix now supports DSPy! What real word use-cases would you like to see?
Lots of requests for richer observability in DSPy.
In March,
@mikeldking
& I are holding a DSPy <>
@arizeai
meetup in SF to show you how to do that w
@ArizePhoenix
-DSPy integration. Video by
@axiomofjoy
.
Good chance to show something cool with DSPy. What would you like to see?
5
28
165
1
6
52
LLM frameworks are game-changing, but the resulting abstractions can be hard to debug. Phoenix now enables you to trace through the execution of your LLM application so you can understand its internals and troubleshoot problems related to things like retrieval and tool execution!
1
5
27
📚
@LangChainAI
@pinecone
@arizeai
Workshop on troubleshooting search and retrieval - the cornerstone of connecting LLMs to private data are VectorDBs and agent frameworks.
3
7
20
🙏
@hwchase17
@UnstructuredIO
@trychroma
on the future of RAG. From time sensitive retrieval to productionizing large vector stores, nothing was off the table.
💡 Try all the new approaches! If you are using RAG, you are on the cutting edge.
0
5
20
@CShorten30
DSPy 🤝 @
@weaviate_io
🤝 Us!
For anyone interested Phoenix is fully open source and fully private 🔐 Your data is your own!
Great work
@CShorten30
! Let us know if there is more visibility you need!
1
7
19
Evaluation 👏 Driven 👏 Development 👏
A critical concept workshop if you are building or tuning a RAG pipeline. Mark your calendars! 📅
Before you try advanced retrieval techniques (query decomposition, reranking, hierarchical chunking, etc.) to improve your RAG pipeline, you should implement evals.
What are the different types of evals?
✅ E2E evals (generated responses)
✅ Retrieval evals (retrieved chunks)
0
18
85
0
3
15
Excited to see what everyone at the
@MistralAI
hackathon with
@cerebral_valley
's been cooking up 👩🍳
If you need to debug your mistral calls, traces might come in super handy . It's as simple as a few lines of code in your app 👇
0
4
14
Phoenix is now integrated with Ragas to help in evaluating and analyzing your RAG pipeline. 🤩
1
2
14
Phoenix is public! Unlock new embedding troubleshooting workflows right in your notebook. Maintained by the
#MLOps
team at
@arizeai
Designed for rapid iteration on your
#LLMs
#ComputerVision
and
#NLP
models.
0
3
13
Huge S/O to
@traviscline
who helped add audio embeddings support to
@ArizePhoenix
and for winning the
@AGIHouseSF
hackathon! Being able to explore your samples using UMAP and HDBSCAN is not just fun, it’s crazy useful for sample discovery 🎧🎶🎼🥁🎸🎹🎺🎻
0
2
13
Struggling with slow iteration cycles & inaccurate
#LLM
responses?🐌😵💫
Sharpen your skills in a hands-on workshop! Learn how to fine-tune & visualize an LLM using
@raydistributed
,
@huggingface
and Phoenix👩💻
Details🔗
#AI
#MachineLearning
#FineTuning
0
4
11
For the full release notes, check out our GitHub. And if you want to see more retrieval troubleshooting tools, give us a ⭐️ and drop us an issue! We'd love to hear from you.
0
1
12
Phoenix +
@MistralAI
= OSS 🫶
phoenix now supports Mistral as well as Mistral instrumentation!
😻 arize-phoenix-evals - use mistral for evals and synthetic data
😻o peninference-instrumentation-mistralai - native instrumentation for the mistralai SDK
Le Chat! 😻
2
5
11
Example of
@AnthropicAI
#LLM
evals dataset loaded into phoenix - The clear vector space of the
#LLM
responses via UMAP is😍and how answer_matches_behavior and label_confidence label directly correlates to the HDBSCAN clusters... 🪄
0
2
11
Not only that, it visually overlays the retrieval connections within the point cloud so you can visually highlight the vector store clusters your retriever is pulling data from. For all the details, check out our notebooks that cover search and retrieval!
1
2
11
Are you fine-tuning your GPT models? Crazy times that fine-tuning is just an API call away. Great insights on how to fine-tune and evaluate LLMs using evals.
Had a really great time chatting with
@aparnadhinak
about fine-tuning and agents at
@ArizeAI
’s LLM event!
1
4
12
0
1
11
LLMOps in a notebook is a game-changer - it lets you leverage the ecosystem. Take ragas - RAG assessment evals library. By combining
@ArizePhoenix
with ragas evals for answer relevancy, context relevancy, and faithfulness, you can QA your app in ways never before possible.
2
1
11
🚀LLM Evals now crank! SIGNIFICANT speedups via concurrency and via carefully managing token limits. We've seen massive speedups in our runs (typically 5x).
When doing EDD, you need to move fast so you can iterate. Crank up the concurrency and see the evals fly!
1
3
10
🧠We have a great workshop coming up with
@llama_index
‘s very own
@jerryjliu0
! It will cover:
☑️ How to build a RAG powered chatbot using
@llama_index
☑️ How to use
@ArizePhoenix
to inspect and analyze retrievals.
✍️ Sign up here!
0
4
10
We are pretty hyped about our new point-cloud tooltips 😶🌫️
0
1
10
#embeddings
are a powerful tool in EDA - even if your model doesn't use them!🤯
@arizeai
provides an AutoEmbeddings package that let's you generate embeddings on your tabular data. You might be surprised what insights you might uncover 🔮
0
4
9
🧪
@arizeai
@jason_lopatecki
using
@ArizePhoenix
and
@llama_index
to figure out rag optimizations and sweet spots for your data. It takes data science rigor to get these things right.
@llama_index
and phoenix's LLM evals play hand-in-hand to give you critical DS workflows.
Adjusting your chunk size is one of the first things you should tackle in improving your RAG app - but it’s not always intuitive!
⚠️ More chunks ≠ better (lost in the middle problems / context overflows)
⚠️ Reranking retrieved chunks doesn’t necessarily improve results, in
5
53
295
0
3
9
We are publishing pre-releases so you can live on the bleeding edge!
In v0.0.23rc0 we've added HDBSCAN tuning so you can get your clusters just right!
Clusters provide an "auto-lasso", helping you identify groups of
#embeddings
that require attention. Check it out!
0
3
9
Phoenix automatically computes the distance between your queries and document embeddings (query distance), helping you quickly identify slices of your data that represent user queries that are not contained in your vector store.
1
0
8
"Haters gonna hate, hate, hate, hate, but this UMAP plot's looking great!"
@Ksquarrd
visualized embedded
@taylorswift13
lyrics with Phoenix 🐦🔥 Can we get the notebook? 📖
Share your insights and be the next to conquer the
#PhoenixChallenge
!
#DataScience
#DataVisualization
Inspired by
@taylorswift13
singing in the rain 'til 2AM, I used
#AI
to analyze 4862 rows of lyrics and explore main
#Swiftie
trends w/
@ArizePhoenix
#TaylorSwift
#DataScience
#Datavisualization
2
8
21
0
0
8
New Phoenix + Ragas cookbook by
@Shahules786
@mikeldking
and
@axiomofjoy
dives into using Ragas for synthetic test generation and evaluation; Phoenix for tracing, visualization and cluster analysis; and
@llama_index
for building RAG pipelines.
0
0
8
Thanks for having us
#AITinkerersWorkshop
@JunaidDawud
🤖the state of generative AI by
@altryne
🌌
#llmops
for your agents and chat it’s by
@arizeai
s Claire!
🤯build amazing worlds using generative AI using
@BlockadeLabs
by
@coin_artist
2
0
7
😍Sneak peak!
We've built composable instrumentation modules under the OpenInference moniker and have published images for the server so that you can run Phoenix as a sidecar to any LLM application. Here's what Phoenix tracing looks like with
@llama_index
's create-llama.
1
0
7
300 ⭐️ Thank you! 🙏 What an amazing few days this have been.
We want to build the best ML Observability platform for your needs. Come build with us!
#starhistory
#GitHub
#OpenSource
via
@StarHistoryHQ
0
2
6
Lots of exciting
@ArizePhoenix
announcements here they come 🎁
Join us in NYC Sept 7 for Building LLM-Powered Systems that Work in the Real World 🙌
Speakers from
@TCVTech
@promptlayer
@bentomlai
@pinecone
@llama_index
@Bazaarvoice
@RogoData
Panels, demonstrations, and networking opportunities!
SAVE YOUR SEAT:
0
1
5
0
1
6
Phoenix LLM Traces get a nice shoutout here from the CTO of
@databricks
! If you are looking for a free OSS tracing solution that integrates with evaluation frameworks, Phoenix is a great fit 😉
Interesting trend in AI: the best results are increasingly obtained by compound systems, not monolithic models.
AlphaCode, ChatGPT+, Gemini are examples.
In this post, we discuss why this is and emerging research on designing & optimizing such systems.
30
263
1K
0
3
6
Thrilled to be a part of the Responsible AI Ecosystem. Let’s build a better AI future for humanity.🕊️
0
1
6
"The downside of that is you have zero visibility into what's actually going on under the hood."
This is exactly why we built tracing - you get full transparency
🟩 documents
🟩 score (cosine / euclidean distance)
🟩 metadata
Retrieval doesn't have to be a black box 📦
Why you should build RAG from scratch 🧑💻
@llama_index
is the
#1
framework for RAG pipelines with >600,000 downloads every month, and yet his creator,
@jerryjliu0
, is encouraging people to reimplement it from scratch at least once. Why?
Not enough people
4
44
279
0
1
6
Export for evals 🧪 and fine-tuning 🤯
The best part? It’s your data! 🔐
Other key features:
Key Features:
✅ LLM input/output prompt template tracking
✅ Token usage and Timing
✅ Full Retrieval observability/visualizations
✅ Full agent support
✅ Export traces for evals
1
1
4
0
1
6
Phoenix 2.1 now has live-updating evaluations and retrieval metrics! Evals are critical to ensuring that your application is benchmarked during pre-production AND production! ☑️ Don't let hallucinations get out of hand 😵💫
1
2
5
Built in Observability at every step. Even in the notebook! 💜
Also huge s/o to
@llama_index
and
@jerryjliu0
- these courses are invaluable.
Introducing a Short Course Series on Advanced RAG Orchestration 🪄🤖
As an AI engineer, it can be daunting to dive into how to build high-quality, advanced RAG yourself - there’s literally hundreds of options at every stage of the pipeline.
Easily stitch together custom modules
5
80
555
0
0
6
🔍 Cluster Search on Embeddings!
Search by keywords in text to get a better understanding of the contents of clusters, identify queries that contain certain words, or even search by ID to find that one embedding you are looking for! Happy troubleshooting! 🌌
0
0
5
If data privacy is paramount for your LLM use-case, let's talk. arize-phoenix runs entirely locally and can be leveraged so that you control your observability and evaluation data end-to-end. Privacy first 🔏
@OpenAI
@Meta
@AnthropicAI
@Google
5. Teams are increasingly concerned about accuracy of responses and hallucinations.
This likely points to the seriousness of adoption and need for tools around governance and LLM observability.
1
2
2
0
0
5
The
@ArizePhoenix
team (
@jason_lopatecki
,
@aparnadhinak
,
@axiomofjoy
,
@aparnadhinak
,
@mikeldking
) are excited to attend this killer
@agihouse_org
event. Excited to hack alongside other builders. 💪
If you're in the Bay don't miss this
@agihouse_org
hackathon this weekend--amazing opportunity to work with founders at
@weaviate_io
@anyscalecompute
@perplexity_ai
, (and us), and more!
OPTIMIZE YOUR LLM STACK:
1
1
2
0
1
5
Phoenix escapes the notebook! We have a docker image version to try out! Perfect for a small docker compose with your LLM app or to just have running so you can persist traces beyond the lifecycle of your notebook.
0
1
5
@jxnlco
@jerryjliu0
@OpenAI
@pydantic
Who knew that using
@pydantic
and json schema to talk to an LLM would become a thing 😅🚅
0
0
5
📆RAG time 🎶
How do you know if you’re using the right chunk size? The right embedding model? Does poor retrieval correlate with hallucinations?
@AstronomerAmber
and
@mikeldking
will be sharing how to benchmark RAG!
Let’s make it a fun one!
0
2
3
Shout out to
@eltociear
for being the first-ever contributor to our open-source project! Thanks for helping us make our documentation better 🙏
1
1
4
👏
@LoganMarkewich
on building this comprehensive guide on LLMs broken down by tasks! Sometimes we just need a 🔴 🟩 indicator to guide us 🤩
The recent
@huggingface
zephyr-7b-alpha model outperforms ChatLlama 70B 😮
We immediately tested it on
@llama_index
easy-to-hard tasks 🧪
We found that it is the ONLY open 7B model atm that does well on advanced RAG/agentic tasks 🔥👇
Colab:
16
166
814
0
0
4
Phoenix for retrieval-augmented generation:
- Automatically identify areas of user interest that are not answered by the knowledge base
- Surface poorly performing queries based on user feedback and LLM-assisted ranking metrics (e.g., precision
@k
)
Debug retrieval-augmented generation with Phoenix 🔥🐦
Check out the notebook below:
0
3
13
0
0
5
Great into to txt to SQL and txt to pandas with
@llama_index
and
@ArizePhoenix
. Great way to supercharge your LLM with tabular data
Advanced QA over a lot of Tabular Data (combine text-to-SQL with RAG) 📊🪄
Our brand-new mini course 🧑🏫 is a comprehensive overview of how you can build simple-to-advanced query pipelines from scratch, by composing components into complex DAGs. Presenting this in three levels:
0
79
315
0
1
4
Tomorrow, 10am PST: Learn how to create an LLM eval from scratch.
Lessons from the trenches with Lou Kratz of
@Bazaarvoice
and
@jason_lopatecki
. ⛏️
Register:
0
1
5
✨Excited to announce evaluations on spans and documents! This means you can evaluate your application as it runs!
@aparnadhinak
explains how LLM evals and explanations can be used in conjunction with traces.
1
0
5
🤩⭐️1⃣5⃣0⃣0⃣⭐️🤩
Thank you so much for the support these past 6 months! We will keep cranking! 🚀
0
0
5
Here's a fully working EDD workflow for you to test out. Uses mistral-large-latest and Mistral Embeddings!
1
0
5
✨ Phoenix 3.0 ✨Phoenix is now a fully OpenTelemetry compliant collector that natively renders rich LLM application data via OpenInference, a set of instrumentations and conventions around observing LLM applications.
1
0
5
Ever wondered what LLMOps is all about? Can't beat a free course on it! 👇
🚀 Accelerate your skills with our free, fast-paced tech course! 🎓 Dive into LLM application deployment for developers, covering fundamentals like:
🔸LLM evals and observability fundamentals
🔸Agents, tools, and chains
🔸And more!
👉
0
5
6
0
0
4
Evaluate
#LLMs
using
@OpenAI
evals.
@ArizePhoenix
can use evals to identify
#embedding
clusters of your LLM application that are performing badly. These clusters are ideal for prompt iteration or fine-tuning
1
3
4
@llama_index
@LangChainAI
arize-phoenix is entirely open-source, built on open standards, and runs entirely in the privacy of your python notebook.
Try it out today and let us know what you think:
Overview: Tracing | Phoenix
Tracing the execution of LLM applications using Telemetry
docs.arize.com
1
0
4
And if you like what we are building - we'd love to hear from you ⭐️
0
0
4
Phoenix was announced at
@arizeai
observe. An amazing conference that really captured the current state of AI. A must watch
Just announced - Phoenix: Open source
#MLObservability
in a notebook! Uncover insights, surface problems, monitor and fine tune your Generative LLM, CV and Tabular Models. Get started:
Learn more here:
0
5
13
0
0
4
As you move your LLM application to production, it’s easy to neglect compliance with things like PII. Plan ahead and safeguard your users from the get go 🔐
Included is a useful code snipit to remove PII from calls to OpenAI/Palm/Bedrock, we just put out the code here for folks to use:
0
1
4
0
0
4
We are the observability sponsor for this great hackathon! Come say hi!
🚀 We're excited to announce the first-ever
@MistralAI
Hackathon in San Francisco on March 23rd-24th at
@SHACK15sf
!
Two days of hacking, and a keynote from Mistral founders
@arthurmensch
&
@GuillaumeLample
A huge shoutout to our sponsors:
@Microsoft
,
@GroqInc
,
@huggingface
,
10
33
154
0
0
4
✨v0.0.20 ✨
We have new support for tabular data! Quickly identify drift and data quality issues in your features using the new dimension details views!
1
2
4
With
#embeddings
distance encodes semantics! This is key to understanding why spatial troubleshooting tools are so important
Semantic search is a very effective way to search documents with a query.
But what exactly does the word “semantic” mean here?
Probably the best way to understand semantic search is to understand what is *not* semantic search.
Let’s take a look. (Thread)
222
2K
24K
0
0
4
@tombielecki
@jerryjliu0
We are actually doing a joint workshop today on RAG troubleshooting using
@llama_index
today! An hour left to sign up!
🧠We have a great workshop coming up with
@llama_index
‘s very own
@jerryjliu0
! It will cover:
☑️ How to build a RAG powered chatbot using
@llama_index
☑️ How to use
@ArizePhoenix
to inspect and analyze retrievals.
✍️ Sign up here!
0
4
10
0
1
4
Great tutorial! Data freshness is something you want to monitor. Are your query embeddings close to the data stored in your vector store? Are there clusters of query embeddings that are under performing? Time for a refresh! ♻️
#llmops
📬 Retrieval augmentation helps us:
- Reduce hallucinations
- Answer Qs on internal / niche datasets
- Cite sources and help users trust LLM output
The future of LLMs will include managed long-term memory like that described here — it's worth learning! 🧑🎓
2
2
12
0
0
4
Great write up by the
@eBay
engineering team on how they built a billion-scale vector similarity engine.
#embeddings
0
0
3
🔥🐦
#PhoenixTipOfTheDay
📖 Phoenix runs in your notebook...literally
🚀 One line of code to launch the app
👀 One line of code to view the app
🪟 You can also open Phoenix in a new browser tab or window if you want more real estate
#PhoenixProTip
#DataScience
0
0
4
Honored to be on this
#ai
power list! ⭐️
23 Open Source AI Libraries for 2023 by
@yujian_tang
According to GitHub Stars, these are listed in order of popularity as of 5/11/23.
Auto-GPT — an open-source LLM framework for autonomous agents
OpenCV — an open source computer vision tool
PyTorch — an open source machine
1
2
4
0
1
4
In our experience, reliably parsing LLM output is half the battle when building
#LLM
applications, especially agents. Excited to check this out
@lmqllang
.
0
0
4
🔊Tune in today for
#RAG
best practices using the new LLM Evals!
Next week we're kicking off our
#llm
Evaluation Essentials series with
@jerryjliu0
of
@llama_index
!
Join us Oct 3 for Benchmarking and Analyzing Retrieval Approaches. A must-attend for
#AI
& ML engineers or anyone seeking production excellence. 🤩
0
1
4
0
0
4
"It's relatively easy to stand up a demo of an LLM workflow…but developing further toward a viable and robust application is another matter."
The DS team
@klickhealth
leverages Phoenix for LLM observability behind-the-scenes:
0
1
4
OpenInference is our OSS spec for ingesting LLM records and is part of
@llama_index
‘s one-click observability! 🪄
[2] OpenInference (
@arize_ai
) is a standard for capturing/storing AI model inferences.
It allows you to experiment/visualize LLM apps using observability tools like
@arize_phoenix
.
Check out the notebook here!
1
0
4
0
1
4
“Traditionally, data is added to an ML model by training the model on that specific data. This leads many to jump to the conclusion that fine tuning LLMs is what is needed. Let’s bust that myth.”
0
2
4
As always, Phoenix is fully OSS, runs in your notebook, and your data is always yours for the keeping 🔒
0
0
3
Truth or meme?
0
0
3
This talk from
@geoffreyhinton
is worth a watch. He warns of the dangers of AI that exceeds human intelligence but isn't aligned with human goals.
Let's build the guardrails to make sure
#AI
systems are
#observable
and
#aligned
.
0
0
3
@axiomofjoy
Instrumentation for
@OpenAI
is a critical building block since it's such a powerful building block for LLM applications and tasks. For the full details, check out the docs on how you can not only trace your LLM calls but evaluate them as well.
1
0
3
How to use F1, Recall, and Precision for RAG evaluation 💯 These metrics are vital QA tools 🧪
Evaluating your LLM system (RAG, agents) is super important 🧪, but what’s the proper methodology for doing so?
There’s two general strategies for evaluating your LLM app:
1️⃣ End-to-end ♾️: First setup the entire pipeline, and then evaluate text inputs/text outputs (don’t
7
30
174
0
0
3
Xander Song, dev advocate at
@arizeai
gives us insight into how
@ArizePhoenix
can be used to troubleshoot / improve your
#llm
and
#computervision
models.
@ArizePhoenix
runs INSIDE your notebook, providing a DX that you might have not known was possible.
0
0
3
Today's the day!
Phoenix is one of 24 open source projects featured this month to help people like you get into open source via simple tutorials and guides.
It’s day 11 of the Open Source Advent!
Today’s featured project is
#Phoenix
by
@arizeai
!
Get all the contest details as we count down to the holidays.
Contest Details:
Contest Discord:
#OSSAdvent2023
1
3
6
0
0
3
“Looking at LLMs as chatbots is the same as looking at early computers as calculators. We're seeing an emergence of a whole new computing paradigm, and it is very early.”
🤯
With many 🧩 dropping recently, a more complete picture is emerging of LLMs not as a chatbot, but the kernel process of a new Operating System. E.g. today it orchestrates:
- Input & Output across modalities (text, audio, vision)
- Code interpreter, ability to write & run
312
2K
10K
0
0
3
Tuning your HDBSCAN parameters for clustering is now easier than ever. Try it out in our latest release 0.0.23.
0
0
3
@llama_index
@LangChainAI
Also new ✨ LLM Evals for hallucinations, relevancy, toxicity, code generation, summarization, and classification. Evaluate the performance of different LLM tasks by leveraging the powerful reasoning skills of an LLM 🧪
1
0
3
2 new eval capabilities on 1.1.0 ✨
Get explanations for LLM Evals via chain-of-thought prompting! 🔍
1
0
3
Open Source Love 🫶 Love Open Source ❣️
Quality insurance is important when you’re designing a production-ready solution for semantic search and vector storage.
Full open source workflow for embedding a large volume of data, uploading to a vector db, running similarity searches, and monitoring it in production.
Learn
2
8
36
0
0
3
Vector DBs form the 🧠s of you LLM powered applications. It’s critical to understand how they leverage
#embeddings
and to monitor how well they encode semantics. The quality of your embeddings directly translate to the quality of your
#LLM
app’s information retrieval.
#LLMOps
Vector databases & embeddings are the current hot thing in AI.
Pinecone, a vector DB company, just raised $100M at ~1b valuation.
Shopify, Brex, Hubspot and others use them for their AI apps
But what are they, how do they work and why are they SO crucial in AI? Let's find out
121
428
3K
0
0
3
Metadata visibility! It’s the little things 😁 Also the cosine/Euclidean distance as well as the embeddings are captured 🌌 there’s never been a tool to give you this much visibility into RAG 🔭
@ArizePhoenix
@llama_index
@LangChainAI
[4] Full Observability into RAG
You can now see what documents were retrieved, metadata of the docs, and even re-ranked results!
1
0
3
0
0
3
1
0
3
“It’s helpful for humans to have a table of contents and well marked chapters for their story, but AI doesn’t care.” -
@BM_DataDowntime
0
0
3
Making sense of embeddings can be overwhelming. Density-based clustering you can start to reason about your embedding's higher-dimensional representation in meaningful groups!
1
0
3
Thanks
@cerebral_valley
on this deep dive 🤿
@ArizePhoenix
has “become almost like our secret weapon of having a tool that helps developers earlier in their journey, and then also throughout the journey of their application.”
@aparnadhinak
Our Deep Dive with
@arizeai
is now live!
ARIZE IS EXPANDING THE FIELD OF AI OBSERVABILITY 📈
Co-founder and CPO
@aparnadhinak
walks us through LLM observability, Phoenix, and their goals for 2024...
Link below 👇
1
4
15
0
0
3