docs(destination-qdrant): correct configuration and setup documentation

[devin-ai-integration]

Triggering Context

Run triggered by: Merged commit on master for destination-qdrant, reported by the autodoc automation (GitHub CI service account).

Relevant context: Commit 6134e8b (version 0.1.42, #84360), which bumped the CDK to remediate CVE-2025-68664 in the langchain dependency.

Confidence impact: The trigger was a small, already-merged dependency bump with unambiguous scope, which supports a high Triggering Context score. The documentation problems this PR fixes are pre-existing and were found while reviewing the connector against its current source, not introduced by the triggering commit.

Documentation Confidence Assessment

Overall Confidence: 3/5

Dimension	Score	Rationale
Code Comprehension of the Documented Surface	4/5	The documented surface is three small Python files plus the shared vector-db CDK config, and every documented field was traced to its Pydantic definition.
API Documentation Quality	4/5	Qdrant publishes thorough docs for installation, interfaces, security, and Cloud authentication, with minor gaps around quotas.
Change Scope & Risk	3/5	59 insertions and 42 deletions, restructuring the setup and configuration sections of a short page.
Existing Doc Maturity	3/5	The page was 139 lines with basic setup and output-schema coverage, but its configuration list did not match the connector spec.
Connector Sensitivity	5/5	Community connector, ql 100 and sl 100, alpha release stage.
Triggering Context	5/5	Triggered from a small merged version bump with clear scope.
Inference Ratio	4/5	Field names, defaults, payload fields, and sync behavior come from source; the gRPC-port guidance comes from qdrant-client source; a few operational cautions are reasonable extrapolation.

Adjustments based on code comprehension

Baseline for a Python CDK connector is 3. Net adjustment +1.

• Framework leverage: upward — Processing, embedding, and advanced options come from VectorDBConfigModel in airbyte_cdk/destinations/vector_db_based/config.py, which the connector inherits unchanged.
• Custom-component budget: upward — The connector-specific path is config.py, indexer.py, and destination.py, roughly 200 lines total, with no dynamic dispatch or feature flags.
• Independent corroboration: upward — Port numbers and authentication behavior are confirmed by both Qdrant's official docs and the connector/client code; _ab_record_id semantics are confirmed by document_processor._extract_primary_key.
• Empirical verification: upward — Read the installed qdrant_client source to confirm that QdrantClient(url=..., prefer_grpc=True) always uses gRPC port 6334 and ignores the port in the URL for gRPC.
• Calibrated self-assessment: downward — Did not run spec against the built image, so the exact UI labels rendered for the authentication oneOf options were not observed; the docs therefore describe those options without quoting their labels.

What I Verified vs. What I Inferred

• Verified from code: the indexing fields and their defaults (url, auth_method defaulting to API key, prefer_grpc defaulting to true, collection, distance_metric defaulting to cosine, text_field defaulting to text); the https-only requirement for API key auth in QdrantIndexer.check; automatic collection creation and the vector-size/distance-metric match check against an existing collection; random UUID point IDs; _ab_stream and _ab_record_id payload fields and their indexes; _ab_record_id being written only for append + deduped streams with a primary key; overwrite deleting points by _ab_stream filter rather than dropping the collection; the processing and advanced options and their required/optional status from the CDK config; the available embedding modes (OpenAI, Azure OpenAI, Cohere, OpenAI-compatible, Fake — from_field is defined in the CDK but not part of this connector's embedding union); gRPC always using port 6334 in qdrant-client.
• Verified from API docs: Qdrant serves REST on 6333 and gRPC on 6334; self-hosted Qdrant has no authentication by default; Qdrant Cloud database API keys are shown only once and can be scoped to specific collections and permissions.
• Inferred: the operational advice to disable Prefer gRPC when only the REST port can be exposed, and the caution about exposing an unauthenticated server; both follow from verified behavior but are not stated in either source.

Areas of Concern

• The previous page told local users to enter Host, Port (example 8000) and a gRPC Port. The connector spec has no such fields, and 8000 is not a Qdrant default. This PR replaces that guidance with the endpoint-URL model the spec actually uses — worth a check that it matches what the UI renders.
• The changelog entry for 0.1.42 was validated: the link text and URL both point to fix(destination-qdrant): bump CDK to remediate CVE-2025-68664 in langchain dependency #84360, and the date 2026-08-13 matches the merge date of the triggering commit. No changelog edit was needed.

---

What

Corrects and restructures docs/integrations/destinations/qdrant.md so it matches the connector's actual configuration spec and behavior. The previous page described a host/port/gRPC-port configuration that the connector does not have, listed optional fields as required (and vice versa), omitted the embedding options the connector supports, and gave 8000 as a local Qdrant port.

How

Corrections

• Replaced the "local mode / cloud mode" host-and-port instructions with the single Public Endpoint URL the spec defines, and documented the correct Qdrant ports: REST 6333, gRPC 6334.
• Fixed required/optional markers for every configuration field and documented their defaults (API key auth, Prefer gRPC enabled, cosine distance, text text field, chunk overlap 0).
• Documented that API key authentication requires an https:// endpoint, which the connection check enforces.
• Replaced the incomplete embedding list (OpenAI, Cohere, "vectors from the source stream") with the modes the connector actually offers.
• Removed the claim that Text fields to embed and Fields to store as metadata are required; both default to all fields.

Additions

• Explained that an existing collection must already match the embedding dimensions and distance metric, or the connection check fails.
• Documented the _ab_stream and _ab_record_id payload fields, and that overwrite mode deletes only the points belonging to the overwritten stream.
• Added the gRPC port implication for network access: with Prefer gRPC enabled, port 6334 must be reachable, since the connector cannot change it.
• Added Qdrant Cloud API key guidance (shown once, needs write access to the target collection) and a note that self-hosted Qdrant is unauthenticated by default.
• Documented the Do not store raw text advanced option.

Restructuring

• Split the flat configuration list into Processing, Embedding, Indexing, and Advanced, matching the groups the connector spec defines, and normalized heading levels (the page previously jumped from # to ####).

Review Guide

• Lines 30–56: rewritten requirements, Qdrant Cloud and self-hosted setup, and network access guidance.
• Lines 58–85: configuration fields grouped as the spec groups them.
• Lines 5–18: output schema, payload fields, and overwrite behavior.
• No changelog rows were changed, and no migration guide was touched.

Requested by the autodoc automation run for commit 6134e8b.

---

Note: I am an AI assistant (Devin) and have proposed these documentation updates based on a review of the connector source code and third-party API documentation. Reviewers may merge, modify, or close this PR as they see fit.

Link to Devin session: https://app.devin.ai/sessions/df5f638587b44583a3554dd1355af71f

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment, CI, and merge conflict monitoring

[github-actions]

👋 Greetings, Airbyte Team Member!

Here are some helpful tips and reminders for your convenience.

💡 Show Tips and Tricks

PR Slash Commands

Airbyte Maintainers (that's you!) can execute the following slash commands on your PR:

• 🛠️ Quick Fixes
  • /format-fix - Fixes most formatting issues.
  • /bump-version - Bumps connector versions, scraping changelog description from the PR title.
    • Bump types: patch (default), minor, major, major_rc, rc, promote.
    • The rc type is a smart default: applies minor_rc if stable, or bumps the RC number if already RC.
    • The promote type strips the RC suffix to finalize a release.
    • Example: /bump-version type=rc or /bump-version type=minor
  • /bump-progressive-rollout-version - Alias for /bump-version type=rc. Bumps with an RC suffix and enables progressive rollout.
• ❇️ AI Testing and Review (internal link: AI-SDLC Docs):
  • /ai-prove-fix - Runs prerelease readiness checks, including testing against customer connections.
  • /ai-canary-prerelease - Rolls out prerelease to 5-10 connections for canary testing.
  • /ai-review - AI-powered PR review for connector safety and quality gates.
• 📝 AI Documentation:
  • /ai-docs-review - AI-powered documentation review for PRs with connector changes.
  • /ai-create-docs-pr - Creates a documentation PR for connector changes, stacked on the current PR.
• 🚀 Connector Releases:
  • /publish-connectors-prerelease - Publishes pre-release connector builds (tagged as {version}-preview.{git-sha}) for all modified connectors in the PR.
  • /enable-autopilot-rollouts - Enables autopilot progressive rollouts for the modified connector(s) in the PR, remediating "autopilot rollouts not enabled for {connector-name}" auto-merge blockers. Sets defaultRolloutMode: autopilot and enableProgressiveRollout: true, preserving any existing autopilotConfig.
    • Optional args: connector=<CONNECTOR_NAME> (defaults to the modified connectors in the PR), strategy=fast|slow|default (defaults to fast).
    • Example: /enable-autopilot-rollouts or /enable-autopilot-rollouts connector=source-faker strategy=slow
• ☕️ JVM connectors:
  • /update-connector-cdk-version connector=<CONNECTOR_NAME> - Updates the specified connector to the latest CDK version.
    Example: /update-connector-cdk-version connector=destination-bigquery
• 🐍 Python connectors:
  • /poe connector source-example lock - Run the Poe lock task on the source-example connector, committing the results back to the branch.
  • /poe source example lock - Alias for /poe connector source-example lock.
  • /poe source example use-cdk-branch my/branch - Pin the source-example CDK reference to the branch name specified.
  • /poe source example use-cdk-latest - Update the source-example CDK dependency to the latest available version.
• ⚙️ Admin commands:
  • /force-merge reason="<REASON>" - Force merges the PR using admin privileges, bypassing CI checks. Requires a reason.
    Example: /force-merge reason="CI is flaky, tests pass locally"

📚 Show Repo Guidance

Helpful Resources

• Breaking Changes Guide - Breaking changes, migration guides, and upgrade deadlines
• Developing Connectors Locally
• Managing Connector Secrets
• On-Demand Regression Tests
• #connector-ci-issues
• #connector-publish-updates
• #connector-build-statuses

📝 Edit this welcome message.

[github-actions]

Deploy preview for airbyte-docs ready!

Project:	airbyte-docs
Status:	✅  Deploy successful!
Preview URL:	https://airbyte-docs-oyecs1yn1-airbyte-growth.vercel.app
Latest Commit:	d3add5e

Deployed with vercel-action