Skip to main content
skill CX Codex

qdrant-migration-tool — Claude Code skill: what it does

The qdrant-migration-tool skill facilitates migrating vector data and metadata from various databases into Qdrant. It orchestrates the migration process, handles data streaming, and manages resume capabilities.

Apache-2.0 137 installs ★ 271 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add qdrant/skills --skill qdrant-migration-tool -a claude-code
Open on GitHub

What qdrant-migration-tool does

The tool operates as a Docker container, streaming data in batches through the machine it runs on. Since it tracks migration progress in an _migration_offsets collection within Qdrant, interrupted tasks resume automatically rather than restarting from scratch.

When working with local database instances, include --net=host in your docker run command to ensure the container can resolve localhost. Note that for sources like Weaviate, Redis, MongoDB, or Solr, you must manually create the target Qdrant collection with matching vector dimensions and distance metrics beforehand. If your connection uses a private CA, mount the certificate via SSL_CERT_FILE to avoid verification failures.

To improve throughput for large migrations, increase --migration.batch-size from its default of 50 to 256 or 512. For Postgres or Qdrant-to-Qdrant migrations, you can additionally tune performance using the --migration.num-workers flag.

What it helps with

  • migrate vector databases like Pinecone or MongoDB to Qdrant
  • resume an interrupted migration process automatically
  • optimize migration throughput for large datasets
  • verify data integrity after migration completion

Example prompts for the agent

  • Help me migrate my vector database to Qdrant
  • How do I resume an interrupted migration to Qdrant?
  • My migration is too slow, how can I speed it up?

How to install qdrant-migration-tool

1Skills CLI (Vercel)

npx skills add qdrant/skills --skill qdrant-migration-tool -a claude-code

2Manually: put the files in place

~/.claude/skills/qdrant-migration-tool/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/qdrant-migration-tool/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about qdrant-migration-tool

How to install qdrant-migration-tool in Claude Code?

Run npx skills add qdrant/skills --skill qdrant-migration-tool -a claude-code in your terminal.

What does qdrant-migration-tool do?

It guides the use of the Qdrant Migration Tool CLI to move vectors and metadata from sources like S3, pgvector, or various cloud services into Qdrant.

What is required to run qdrant-migration-tool?

You need Docker installed to run the migration container from registry.cloud.qdrant.io/library/qdrant-migration.

Source text

SKILL.md · Apache-2.0
---
name: qdrant-migration-tool
description: "Guides use of the Qdrant Migration Tool CLI to move vectors, metadata, and sparse embeddings from another vector database into Qdrant. Use when someone asks 'how do I migrate from Pinecone/Weaviate/Milvus/Elasticsearch/OpenSearch/pgvector/s3/Azure/DynamoDB/Turbopuffer/Chroma/Redis/MongoDB/FAISS/Solr to Qdrant', 'move my vector database to Qdrant', 'is there a migration tool for Qdrant', 'my migration got interrupted, how do I resume it', 'migration is too slow', or 'collection wasn't created after migration'. Also use when picking migration batch size, deciding on `--net=host`, or verifying data after a migration."
---

# Qdrant Migration Tool

The tool is a Docker container (`registry.cloud.qdrant.io/library/qdrant-migration`), not a library you import. It streams data in batches through the machine it runs on rather than connecting source and target directly, and it resumes by default rather than restarting from scratch. [Migrate to Qdrant](https://skills.qdrant.tech/md/documentation/migrate-to-qdrant/)

## Picking the Right Subcommand

Use when: starting a new migration and choosing the source-specific CLI subcommand.

- Each source has its own subcommand, listed in the [Supported Sources](https://skills.qdrant.tech/md/documentation/migrate-to-qdrant/?s=supported-sources) table; most are named after the source, the non-obvious ones are `pg` (pgvector), `s3` (S3 Vectors), and `azure` (Azure AI Search).
- Weaviate, Redis, MongoDB, and Apache Solr do not auto-create the target collection; create it in Qdrant first with matching vector size and distance metric before running the migration. All other sources auto-create it.
- Read the source's guide (linked from the same table) before running the migration: credentials and concept mapping (namespaces, indexes, metadata fields) are source-specific.
- Source not listed? Point to the GitHub issue tracker rather than improvising a custom pipeline. [Open an issue](https://github.com/qdrant/migration/issues)

## Running Against Local Instances

Use when: either the source or target database runs on the same machine as the migration container.

- Add `--net=host` to the `docker run` command; without it, the container cannot resolve `localhost` on the host machine. [Migrate to Qdrant](https://skills.qdrant.tech/md/documentation/migrate-to-qdrant/)
- Run the container on a machine with low latency to both databases. Direct source-target connectivity is not required since the tool streams through wherever it runs, but round trips from the migration host to each database still add up.

## Migration Was Interrupted

Use when: a migration stopped partway through and needs to continue, or needs to be re-run from zero.

- Re-run the exact same command. Progress is tracked in the `_migration_offsets` collection in Qdrant, so it resumes automatically rather than re-copying already-migrated points.
- Pass `--migration.restart` to discard saved progress and start over, e.g. after fixing a bad source-side filter or changing collection schema mid-migration.
- Custom offsets-collection name only matters if you're running multiple concurrent migrations into the same Qdrant instance; otherwise leave `--migration.offsets-collection` at its default to avoid tracking state you'll forget to look for later.

## Migration Is Too Slow

Use when: throughput is too low for the size of the source dataset.

- Raise `--migration.batch-size` from the default of 50 to 256 or 512 for large migrations; small batches under-use each upsert round trip.
- `--migration.num-workers` only exists for the `pg` and `qdrant` subcommands; other sources have no parallel-worker flag, so throughput there is bounded by batch size and network proximity alone.
- `--migration.batch-delay` defaults to 0; only raise it deliberately to throttle load on a source database that can't absorb full-speed reads, not as a default tuning knob.

## After Migration

Use when: the migration command finished and data needs to be trusted before cutting over traffic.

- Run through the verification framework rather than spot-checking a few points: it covers pre-migration baselines, data integrity checks, and search-quality validation, not just point counts. [Migration Verification Guide](https://skills.qdrant.tech/md/documentation/migration-guidance/)
- If Postgres/pgvector stays live alongside Qdrant post-migration, set up an ongoing sync strategy (event-driven, batch, or dual-write) instead of treating the migration as a one-time cutover. [Keeping Postgres in Sync](https://skills.qdrant.tech/md/documentation/data-synchronization/)

## What NOT to Do

- Assume Weaviate, Redis, MongoDB, or Solr auto-create the target collection; these sources don't expose vector dimensions or distance metric to the tool, so the collection must be created manually first with settings that exactly match the source. [Migrate to Qdrant](https://skills.qdrant.tech/md/documentation/migrate-to-qdrant/)
- Point the `faiss` subcommand at a quantized FAISS index; only `IndexFlatL2`, `IndexFlatIP`, `IndexHNSWFlat`, and `IndexIVFFlat` are supported, since quantized indexes don't retain the original vectors. [FAISS](https://skills.qdrant.tech/md/documentation/migrate-to-qdrant/from-faiss/)
- Assume every Pinecone index can be migrated; only serverless indexes support the list operation the tool needs to enumerate vectors.[Pinecone](https://skills.qdrant.tech/md/documentation/migrate-to-qdrant/from-pinecone/)
- Run a `qdrant`-to-`qdrant` migration into an existing target collection without checking its vector size first; source and target dimensions must match exactly, only replication and shard settings are allowed to differ.
- Connect over TLS to a source or target signed by a private or self-signed CA without mounting it via `SSL_CERT_FILE`; the migration fails on certificate verification instead of degrading gracefully, and `--skip-tls-verification` should be a deliberate override, not a default fix. 
- Pass `--migration.restart` out of caution on a healthy resume; it discards saved progress and re-streams data that already migrated.
- Treat a completed migration run as verified without running data integrity and search quality checks.

© qdrant · Apache-2.0 · qdrant/skills

Similar skills

All skills for Data and databases →

From the same set12

The whole set →
qdrant-version-upgrade The qdrant-version-upgrade Claude Code skill guides Qdrant server and SDK upgrades with version compatibility in mind. It covers upgrade sequencing, multi-version jumps, and behavior changes after a release. CX Codex +1 1,400installs qdrant-performance-optimization qdrant-performance-optimization — a routing skill for Qdrant tuning: it matches your symptom to the right sub-skill for search speed, indexing or memory. CX Codex +1 1,700installs qdrant-advisor qdrant-advisor fetches official troubleshooting guidance live from skills.qdrant.tech to diagnose vector search latency, memory spikes, and sharding issues. CX Codex +1 782installs qdrant-edge This Claude Code skill guides development with Qdrant Edge. It covers local shard sync, BM25 search, and index maintenance. CX Codex +1 328installs qdrant-multitenancy qdrant-multitenancy — a skill for Claude Code, Codex, and Cursor. Guides tenant isolation architecture across users in Qdrant vector databases. CX Codex +1 298installs qdrant-sizing qdrant-sizing calculates RAM, disk space, CPU cores, and node count for a Qdrant deployment before hardware or cloud instances are provisioned. CX Codex +1 222installs qdrant-hybrid-cloud-setup The qdrant-hybrid-cloud-setup Claude Code skill guides Qdrant Hybrid Cloud deployment on a self-managed Kubernetes cluster. It activates for agent and operator setup, storage and backups, or cluster access configuration. CX Codex +1 121installs qdrant-skills This plugin gives the agent Qdrant guidance for scaling, search quality, SDK work, deployments, monitoring, and model changes. ★ 271repo stars

More in the catalog

Project sponsors

Companies that keep this analytics open