Registry / llm-agents / llama-index-vector-stores-elasticsearch

llama-index-vector-stores-elasticsearch

library0.6.0pypypi✓ verified 85d ago

Elasticsearch vector store integration for LlamaIndex. Provides ElasticsearchStore for indexing and querying vector embeddings with full Elasticsearch features. Current version: 0.6.0. Release cadence: follows llama-index releases.

llm-agents vector-search ai-ml

pip install llama-index-vector-stores-elasticsearch

package ↗

INSTALL

IMPORT

SIG · LLAMA-INDEX-VECTOR

llama-index-vector-stores-elasticsearch

llm-agentspythonv0.6.0

Install

18.9s avg

Import

6934ms

Disk

260MB

Pass rate

10/ 10

Env Coverage10 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.6.0 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

installs and imports cleanly · install 0.0s · import 5.808s · 248.5MB

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 18.9s · import 5.286s · 245MB

260MB installed

● package 260MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

ElasticsearchStore

✓ from llama_index.vector_stores.elasticsearch import ElasticsearchStore

Official import path.

Initialize an ElasticsearchStore with environment variables for credentials.

import os from llama_index.vector_stores.elasticsearch import ElasticsearchStore vector_store = ElasticsearchStore( index_name="my_index", es_url=os.environ.get("ES_URL", "http://localhost:9200"), es_user=os.environ.get("ES_USER", "elastic"), es_password=os.environ.get("ES_PASSWORD", "changeme"), ) print("Elasticsearch store created successfully.")

Debug

Known issues

breakingIn version 0.6.0, the parameter `es_url` replaced the deprecated `host` and `port` parameters. Code using old parameters will fail.

fix

Use `es_url` instead of `host` and `port`.

affects: <0.6.0

deprecatedThe `distance_strategy` parameter is deprecated in favor of using `similarity` parameter with values like "cosine" or "l2".

fix

Replace `distance_strategy="COSINE"` with `similarity="cosine"`.

affects: >=0.6.0

gotchaElasticsearchStore does not automatically create the index if it doesn't exist. You must either pre-create the index with appropriate mappings or use the `create_index` parameter.

fix

Set `create_index=True` when initializing the store, or manually create the index with proper dense_vector field mapping.

affects: all

gotchaWhen using authentication, ensure you pass both `es_user` and `es_password`. Passing only one may lead to unexpected connection errors.

fix

Always provide both user and password or use API key authentication.

affects: all

Errors

Common errors & fixes

elasticsearch.BadRequestError: BadRequestError(400, 'x_content_parse_exception', 'failed to parse field [mappings.properties.embedding]')

Elasticsearch index already exists with incorrect mapping for the embedding field (e.g., wrong dimension or type).

fix

Delete the existing index and let the store recreate it with correct mapping, or update the index mapping to match the expected dense_vector type.

AttributeError: module 'llama_index.vector_stores.elasticsearch' has no attribute 'ElasticsearchStore'

Old import path: from llama_index.vector_stores import ElasticsearchStore (incorrect).

fix

Use the correct import: from llama_index.vector_stores.elasticsearch import ElasticsearchStore

Upgrade

Version history

0.6.0latest on PyPI · released Mar 12, 2026

Audit

Dependencies

elasticsearchrequiredRequired for connecting to Elasticsearch instance.

llama-index-corerequiredCore dependency for vector store interface.

Agent activity

36 hits · last 30 days

node

OpenAI (training)

Resources

packagehttps://pypi.org/project/llama-index-vector-stores-elasticsearch/ ↗