Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

elasticsearch: check for deployed models #18973

Merged
merged 2 commits into from
Mar 19, 2024
Merged

elasticsearch: check for deployed models #18973

merged 2 commits into from
Mar 19, 2024

Conversation

maxjakob
Copy link
Contributor

When creating a new index, if we use a retrieval strategy that expects a model to be deployed in Elasticsearch, check if a model with this name is indeed deployed before creating an index. This lowers the probability to get into a state in which an index was created with a faulty model ID, which cannot be overwritten any more (the index has to manually be deleted).

@efriis efriis added the partner label Mar 12, 2024
@efriis efriis self-assigned this Mar 12, 2024
Copy link

vercel bot commented Mar 12, 2024

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Ignored Deployment
Name Status Preview Comments Updated (UTC)
langchain ⬜️ Ignored (Inspect) Visit Preview Mar 12, 2024 2:27pm

@maxjakob maxjakob changed the title elasticsearch elasticsearch: check for deployed models Mar 12, 2024
@maxjakob maxjakob marked this pull request as ready for review March 12, 2024 14:43
@dosubot dosubot bot added size:M This PR changes 30-99 lines, ignoring generated files. Ɑ: vector store Related to vector store module 🔌: elasticsearch Primarily related to elastic/elasticsearch integrations 🤖:improvement Medium size change to existing code to handle new use-cases labels Mar 12, 2024
@hwchase17 hwchase17 merged commit 6f544a6 into langchain-ai:master Mar 19, 2024
20 checks passed
gkorland pushed a commit to FalkorDB/langchain that referenced this pull request Mar 30, 2024
When creating a new index, if we use a retrieval strategy that expects a
model to be deployed in Elasticsearch, check if a model with this name
is indeed deployed before creating an index. This lowers the probability
to get into a state in which an index was created with a faulty model
ID, which cannot be overwritten any more (the index has to manually be
deleted).
chrispy-snps pushed a commit to chrispy-snps/langchain that referenced this pull request Mar 30, 2024
When creating a new index, if we use a retrieval strategy that expects a
model to be deployed in Elasticsearch, check if a model with this name
is indeed deployed before creating an index. This lowers the probability
to get into a state in which an index was created with a faulty model
ID, which cannot be overwritten any more (the index has to manually be
deleted).
hinthornw pushed a commit that referenced this pull request Apr 26, 2024
When creating a new index, if we use a retrieval strategy that expects a
model to be deployed in Elasticsearch, check if a model with this name
is indeed deployed before creating an index. This lowers the probability
to get into a state in which an index was created with a faulty model
ID, which cannot be overwritten any more (the index has to manually be
deleted).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
🔌: elasticsearch Primarily related to elastic/elasticsearch integrations 🤖:improvement Medium size change to existing code to handle new use-cases partner size:M This PR changes 30-99 lines, ignoring generated files. Ɑ: vector store Related to vector store module
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants