haystack icon indicating copy to clipboard operation
haystack copied to clipboard

:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d...

Results 849 haystack issues
Sort by recently updated
recently updated
newest added

**Is your feature request related to a problem? Please describe.** Currently the pre-commit hook can check and fix missing docs in the API but it has no effect if you...

Contributions wanted!
topic:tests

**Is your feature request related to a problem? Please describe.** `BaseDocumentStore`'s `get_all_documents` supports `return_embedding` as method param but `get_document_by_id` does not. This is inconsistent and a bit confusing. **Describe the...

type:feature
good first issue
Contributions wanted!
topic:document_store
journey:first steps

As a devops engineer I want to know roughly how much time a request spends in each node. **Is your feature request related to a problem? Please describe.** Currently we...

action:needs documentation
type:feature
topic:speed
topic:pipeline
journey:advanced

As a datascientist I don't want my logs to be cluttered with devops infos. **Is your feature request related to a problem? Please describe.** Currently we do not separate logs...

action:needs documentation
type:feature
journey:advanced

As a haystack user I want to know how to configure advanced logging features as introduced in #3003 and #3004. **Is your feature request related to a problem? Please describe.**...

type:documentation
journey:advanced

**Is your feature request related to a problem? Please describe.** Code instrumentation and machine-readable logs are instrumental to make monitoring and alerting easier when Haystack is part of a production...

epic
2.x

**Related Issue(s)**: [Issue #1512 ](https://github.com/deepset-ai/haystack/issues/1512) [Issue #1222](https://github.com/deepset-ai/haystack/issues/1222) **Proposed changes**: Migrating to Pytorch's native AMP https://pytorch.org/docs/stable/notes/amp_examples.html because it is much easier to use (no additional dependency on apex) and needs fewer...

action:needs documentation
topic:speed
breaking change

**Describe the bug** - `Pipeline.run_batch()` fails on indexing pipelines. - The failure is early and seems to occur in the `run_batch` method itself - The failure seems trivial **Error message**...

type:bug
Contributions wanted!
topic:pipeline
journey:first steps

Rewrite of https://github.com/deepset-ai/haystack/pull/2675#issuecomment-1195487118 ### Related Issues - fixes https://github.com/deepset-ai/haystack/issues/2672 ### Proposed Changes: > Will match a field that contains all values in the list, no more, no less. Order does...

type:bug
topic:elasticsearch
topic:document_store
journey:first steps

This issue is easily reproducible in FAISSDataStore and SQLDataStore. When the value of the key in doc.meta is set to a list, then document_store.write fails. This happens when I'm using...

type:bug
good first issue
Contributions wanted!
topic:file_converter
topic:metadata
journey:first steps