Victoria Slocum
@victorialslocum
/in/victorialslocum
Machine Learning Engineer
MY
TEAM
(responsibly)
struggles
successes
a part of the whole
It's often hard to get structured, reliable outputs with LLMs in a way that you can ensure complete accuracy. They are statistical models.
New AI developments, like LLMs and vector databases have made problems that have historically been very hard to solve or do well much easier.
I believe in the importance of building trustable and transparent systems, tools that can easily integrate with each other, and providing best-practice education.
From beginning to end
Involving the community
Being an ecosystem
Offer support for projects of all sizes, from different index constructions, compression features, easy deployment options, search types.
Everything has good defaults to get started with something that works right away, but many options for further customizability.
We love our community - offering support through tons of educational resources, an open roadmap where you can vote for features, and even incentive programs like the Weaviate Hero.
We provide a ton of easy integrations to other companies and products, like OpenAI, LlamaIndex, LangChain, Haystack, Cohere, ...
Part of being an AI company means recognizing the power of an ecosystem of amazing products that can work together.
We
Hackathons
Building an
advanced
medical RAG
use case
Can we build an AI powered doctor assistant?
Understands meaning, rather than just exact matching
Medicine has a lot of specific keywords you might want to use in the search for relevant cases/articles
reviews = client.collections.get("WineReviewNV")
response = reviews.query.hybrid(
query="A French Riesling",
target_vector="title_country",
limit=3
)
for o in response.objects:
print(o.properties)
MedCPT Query Encoder: compute the embeddings of short texts
MedCPT Article Encoder: compute the embeddings of patient cases & articles
If you use a LLM fine-tuned on medical domain data it can perform better
Meditron-70B open-source medical LLM: trained on 48.1B tokens from the medical domain.
task = "What do these animals have in common, if anything?"
jeopardy = client.collections.get("JeopardyQuestion")
response = jeopardy.generate.near_text(
query="Cute animals",
limit=3,
grouped_task=task
)
# print the generated response
print(response.generated)
Get more specific results, instead of just top k
We can use LLMs to re-write both the prompt (DSPy) and the query to the vector DB
Sift through top returned patient cases and re-rank them based on relevance!
jeopardy = client.collections.get("JeopardyQuestion")
response = jeopardy.query.near_text(
query="flying",
limit=10,
rerank=wvc.query.Rerank(
prop="question",
query="publication"
),
return_metadata=wvc.query.MetadataQuery(score=True)
)
for o in response.objects:
print(o.properties)
print(o.metadata.score)