Weaviate vs HelixDB

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round drawn
   Weaviate✓fullprobed9/10

   A probe confirms Weaviate hosts a working llms.txt at docs.weaviate.io/llms.txt returning HTTP 200 with structured summary content, and Weaviate also documents an official MCP server for agent/IDE integration, directly supporting agent-oriented docs consumption. Missing for 10: independent third-party confirmation that agents actually consume and act on this llms.txt in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.weaviate.io/llms.txt # Weaviate ## TL;DR Weaviate is an open-source vector database (Go) that sto…”
   • [probe] “official MCP server documented at https://github.com/weaviate/mcp-server-weaviate”
   • [claimed-docs] “Enable and configure the Weaviate MCP server so LLMs and IDE assistants can interact with your Weaviate instance.”

   proof ↗⚑ flag

   HelixDB✓fullprobed9/10

   A probe confirms a live, working llms.txt at docs.helix-db.com/llms.txt describing HelixDB for agent consumption, and the docs/GitHub bootstrapper (helix chef) explicitly installs 'docs MCP' to let agents query docs directly, reinforcing agent-oriented documentation access. Missing for 10: independent (non-vendor) confirmation that agents actually consume and act correctly on the llms.txt content.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.helix-db.com/llms.txt # HelixDB > HelixDB combines a property graph, approximate vector search, an…”
   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”
   • [probe] “official MCP server documented at https://docs.helix-db.com/database/helix-cloud/connect/mcp”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round drawn
   Weaviate~partialclaimed6/10

   Weaviate ships as a headless server deployable via Docker/Kubernetes with official client libraries (Python, JS, Go, Java) for programmatic access, which supports scripted/CI automation (weaviate-gh-2, weaviate-gh-3, weaviate-docs-21). However, there is no explicit documentation or example of running Weaviate specifically within a CI pipeline or automated test/deploy workflow. Missing for 10: explicit CI/CD integration guides, non-interactive automation examples, and independent confirmation of headless CI usage.

   • [github] “You can easily start Weaviate and a local vector embedding model with Docker.”
   • [github] “Weaviate offers multiple installation and deployment options: Docker, Kubernetes, Weaviate Cloud”
   • [claimed-docs] “Follow the instructions below to install one of the official client libraries, available in Python, JavaScript/TypeScript, Go, and Java.”

   proof ↗⚑ flag

   HelixDB~partialprobed6/10

   Docs show a CLI-driven quickstart (initialize, start a local instance, run query, stop it) and an embedded in-process mode, both of which are amenable to scripting/CI automation, and a CLI is documented separately. However, there is no explicit CI/CD example, non-interactive flag documentation, or Docker/headless deployment guidance in the pack. missing for 10: explicit CI pipeline example, non-interactive/headless flags, containerized automation docs.

   • [claimed-docs] “Initialize HelixDB, start a local instance, run the generated query, and stop it”
   • [claimed-docs] “Embedded database — run the same engine and queries in process with memory, disk, or object storage.”
   • [probe] “official CLI documented at https://docs.helix-db.com/cli/getting-started”
   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”

   proof ↗⚑ flag

3. ai-native userConnect an agent via an official MCP server

   weight 3 · round to Weaviate
   Weaviate✓fullprobed8/10

   Weaviate documents an official MCP server that lets LLMs/IDE assistants interact with a Weaviate instance, with both docs and a dedicated GitHub repo confirming it. Missing for 10: independent hands-on validation/community corroboration of the MCP server's reliability and depth of tool coverage.

   • [claimed-docs] “Enable and configure the Weaviate MCP server so LLMs and IDE assistants can interact with your Weaviate instance.”
   • [probe] “official MCP server documented at https://github.com/weaviate/mcp-server-weaviate”

   proof ↗⚑ flag

   HelixDB✓fullprobed7/10

   HelixDB documents an official MCP server (helix-cloud/connect/mcp) with tools like helix_execute_read_query requiring scoped permissions, and a probe confirms this MCP endpoint exists; the helix chef bootstrapper also installs a 'docs MCP'. Missing for 10: independent/hands-on confirmation of an agent successfully connecting via this MCP server, and fuller documentation of the full tool set beyond read queries.

   • [claimed-docs] “helix_execute_read_query: execute exact v3 request_type: "read" JSON; requires database.query.read.”
   • [probe] “official MCP server documented at https://docs.helix-db.com/database/helix-cloud/connect/mcp”
   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to HelixDB
   Weaviate—none0/10

   Evidence lists official client libraries (Python, JS/TS, Go, Java) and an MCP server, but no mention anywhere of an official CLI tool for interacting with or managing Weaviate.

   • [claimed-docs] “Follow the instructions below to install one of the official client libraries, available in Python, JavaScript/TypeScript, Go, and Java.”
   • [probe] “official MCP server documented at https://github.com/weaviate/mcp-server-weaviate”

   proof ↗⚑ flag

   HelixDB✓fullprobed7/10

   HelixDB ships an official CLI (documented at docs.helix-db.com/cli/getting-started) used for init/start/stop workflows and a 'helix chef' bootstrapper that installs AI query skills, scaffolds projects, and seeds data — clearly geared toward AI-native/agentic workflows. missing for 10: independent hands-on confirmation of the CLI's AI-specific features and no detail on full command surface beyond quickstart/bootstrap.

   • [probe] “official CLI documented at https://docs.helix-db.com/cli/getting-started”
   • [claimed-docs] “Initialize HelixDB, start a local instance, run the generated query, and stop it”
   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”

   proof ↗⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round drawn
   Weaviate✓fullprobed8/10

   Weaviate exposes official documented client libraries (Python, JS/TS, Go, Java) and REST/GraphQL APIs for driving all core operations (collections, hybrid search, RAG, multi-tenancy), plus a documented official MCP server enabling LLMs/IDE assistants to interact with instances, confirming programmatic, agent-friendly access. missing for 10: independent hands-on validation of API completeness/stability and no direct evidence of OpenAPI/REST spec docs beyond client libraries.

   • [claimed-docs] “Follow the instructions below to install one of the official client libraries, available in Python, JavaScript/TypeScript, Go, and Java.”
   • [claimed-docs] “Enable and configure the Weaviate MCP server so LLMs and IDE assistants can interact with your Weaviate instance.”
   • [probe] “official MCP server documented at https://github.com/weaviate/mcp-server-weaviate”
   • [github] “Weaviate supports two approaches to store vectors: automatic vectorization at import using integrated models ... or direct import of pre-com…”
   • [claimed-docs] “Import objects directly into Weaviate without having to manually specify embeddings”

   proof ↗⚑ flag

   HelixDB✓fullprobed8/10

   HelixDB exposes a documented, machine-readable public API surface: an OpenAPI spec (helixdb-probe-2), an llms.txt for LLM consumption (helixdb-probe-1), a unified operation-tree request model across Rust/TypeScript/Go/Python SDKs (helixdb-docs-6), a documented CLI (helixdb-probe-4), and an official MCP server with concrete tool definitions like helix_execute_read_query (helixdb-docs-8, helixdb-probe-3). This gives an AI-native user multiple first-party, documented entry points to drive the product programmatically. Missing for 10: independent/hands-on corroboration that the documented API surface is complete and stable in practice (community comments focus on the HelixQL query language's AI-friendliness rather than the API/documentation itself, so they don't concretely contradict this story).

   • [claimed-docs] “HelixDB v3 uses one operation-tree request model across the Rust, TypeScript, Go, and Python SDKs.”
   • [claimed-docs] “helix_execute_read_query: execute exact v3 request_type: "read" JSON; requires database.query.read.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.helix-db.com/llms.txt # HelixDB > HelixDB combines a property graph, approximate vector search, an…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.helix-db.com/openapi.json — contains "openapi" key”
   • [probe] “official MCP server documented at https://docs.helix-db.com/database/helix-cloud/connect/mcp”
   • [probe] “official CLI documented at https://docs.helix-db.com/cli/getting-started”

   proof ↗⚑ flag

6. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to HelixDB
   Weaviate—none0/10

   No evidence of scoped/least-privilege API key or credential issuance for agents; docs cover multi-tenancy, RBAC-adjacent isolation, and MCP server setup but nothing about generating restricted-scope API credentials specifically for agent use. Missing for 10: any mention of API key scoping, role-based permission grants, or credential minting workflow for agents.

   • [claimed-docs] “Enable and configure the Weaviate MCP server so LLMs and IDE assistants can interact with your Weaviate instance.”
   • [probe] “official MCP server documented at https://github.com/weaviate/mcp-server-weaviate”
   • [claimed-docs] “Multi-tenancy provides data isolation. Each tenant is stored on a separate shard. Data stored in one tenant is not visible to another tenant…”

   proof ↗⚑ flag

   HelixDB✓fullclaimed7/10

   HelixDB docs explicitly describe scoped API keys with read-only, read-write, or operation-restricted permissions for least-privilege credentials per service/environment (RBAC), and the MCP tool docs show specific permission scopes (e.g., database.query.read) required per operation, directly matching the story for issuing scoped credentials to an agent. Missing for 10: independent/hands-on verification that these scoped keys work as documented in practice, and more detail on credential issuance workflow (e.g., via CLI/dashboard) rather than just a feature description.

   • [claimed-docs] “Role-based access control. Scoped API keys with read-only, read-write, or operation-restricted permissions for least-privilege credentials p…”
   • [claimed-docs] “helix_execute_read_query: execute exact v3 request_type: "read" JSON; requires database.query.read.”
   • [claimed-docs] “Database-specific overrides can change the sustained rate, burst capacity, and query attempt budget.”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round drawn
   Weaviate✓fullcommunity8/10

   Weaviate documents official client libraries in Python, JavaScript/TypeScript, Go, and Java, which are the primary SDKs for building AI-native applications against the database. Missing for 10: independent hands-on corroboration of SDK quality/completeness and explicit coverage of async support issues raised by a community user.

   • [claimed-docs] “Follow the instructions below to install one of the official client libraries, available in Python, JavaScript/TypeScript, Go, and Java.”
   • [community] “Just migrated from Supabase + pgvector to Weaviate hoping to take advantage of langchain.retrievers.weaviate_hybrid_search.WeaviateHybridSea…”

   proof ↗⚑ flag

   HelixDB✓fullprobed8/10

   HelixDB documents official SDKs across Rust, TypeScript, Go, and Python built on a unified v3 operation-tree request model, plus a CLI and MCP integration for AI-native tooling. Missing for 10: independent hands-on validation of SDK quality/parity and more detail on SDK-specific docs beyond the overview page.

   • [claimed-docs] “HelixDB v3 uses one operation-tree request model across the Rust, TypeScript, Go, and Python SDKs.”
   • [probe] “official CLI documented at https://docs.helix-db.com/cli/getting-started”
   • [probe] “official MCP server documented at https://docs.helix-db.com/database/helix-cloud/connect/mcp”
   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Weaviate—none0/10

   No evidence in the pack mentions webhooks or event subscription mechanisms; Weaviate's documented features cover search, RAG, multi-tenancy, replication, backups, and MCP integration but nothing about webhook-based event subscriptions.

   ⚑ flag

   HelixDB—none0/10

   No evidence of webhook subscription or event-notification capability anywhere in the docs, CLI, MCP, or API references; the evidence covers queries, indexes, security, and multi-tenancy but nothing about event-driven webhooks.

   ⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to Weaviate
   Weaviate~partialclaimed6/10

   Weaviate's docs show generative/RAG features that produce natural-language answers from data (docs-6/23), a dedicated agentic 'Query Agent' for agentic search over collections (docs-27), and RAG-oriented backend claims (docs-3, gh-4) plus agent integrations leveraging semantic insights (docs-4) — this directly matches 'AI-generated insights from data'. However the natural-language Q&A feature is explicitly marked 'Cloud only' (docs-23), and there is no independent/hands-on evidence validating quality or reliability of these generated insights, only vendor docs. Missing for 10: independent corroboration of generated-insight quality, self-hosted parity for the Q&A/insights feature, and concrete examples of Query Agent output.

   • [claimed-docs] “Weaviate can serve as a robust backend for RAG workflows, where vector search is used to retrieve context that enhances the output of genera…”
   • [claimed-docs] “These agents can leverage semantic insights to make decisions or trigger actions based on the data stored in Weaviate.”
   • [claimed-docs] “Get answers from your data by using a natural language prompt/question.”
   • [claimed-docs] “Get answers from your data by using a natural language prompt/question. Cloud only”
   • [claimed-docs] “Query Agent: Run agentic search over your Weaviate Cloud collections”
   • [github] “It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface…”

   proof ↗⚑ flag

   HelixDB—none0/10

   The evidence describes HelixDB as a graph/vector/text database with MCP-based query access and an AI-assisted bootstrapper for scaffolding, but there is no mention of the product itself generating insights, summaries, or suggestions from stored data — it only lets external AI agents issue read/write queries against the data.

   ⚑ flag

2. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Weaviate
   Weaviate~partialclaimed5/10

   Weaviate Cloud ships a 'Query Agent' described as agentic search that can be delegated over your collections, and docs mention agents leveraging semantic insights to trigger actions, which is a form of built-in AI delegation. However this is narrow (search-only, Cloud-only) rather than a general-purpose in-product assistant, and there's no independent/hands-on corroboration of its use. Missing for 10: broader task delegation beyond search, self-hosted availability, and third-party validation of the Query Agent's real-world behavior.

   • [claimed-docs] “Query Agent: Run agentic search over your Weaviate Cloud collections”
   • [claimed-docs] “These agents can leverage semantic insights to make decisions or trigger actions based on the data stored in Weaviate.”
   • [claimed-docs] “Get answers from your data by using a natural language prompt/question. Cloud only”

   proof ↗⚑ flag

   HelixDB—none0/10

   HelixDB documents an MCP server for external AI agents/tools to connect to it, and a 'helix chef' bootstrapper that scaffolds projects, but there is no evidence of a built-in AI assistant inside the product itself that a user can delegate tasks to.

   • [claimed-docs] “helix_execute_read_query: execute exact v3 request_type: "read" JSON; requires database.query.read.”
   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”
   • [probe] “official MCP server documented at https://docs.helix-db.com/database/helix-cloud/connect/mcp”

   proof ↗⚑ flag

3. ai-native userOperate the product with natural-language commands

   weight 2 · round to Weaviate
   Weaviate✓fullprobed7/10

   Weaviate documents both natural-language query answering ("Get answers from your data by using a natural language prompt/question") and an official MCP server enabling LLMs/IDE assistants to interact with a Weaviate instance, plus a 'Query Agent' for agentic search over collections — together these let an AI-native user operate the DB via natural-language commands rather than only structured queries. Missing for 10: independent/hands-on verification that NL commands reliably drive full CRUD/admin operations (not just search), and no community corroboration of MCP/Query Agent quality in practice.

   • [claimed-docs] “Get answers from your data by using a natural language prompt/question.”
   • [claimed-docs] “Get answers from your data by using a natural language prompt/question. Cloud only”
   • [claimed-docs] “Enable and configure the Weaviate MCP server so LLMs and IDE assistants can interact with your Weaviate instance.”
   • [claimed-docs] “Query Agent: Run agentic search over your Weaviate Cloud collections”
   • [probe] “official MCP server documented at https://github.com/weaviate/mcp-server-weaviate”

   proof ↗⚑ flag

   HelixDB!disputedcontradicted3/10

   HelixDB offers an MCP server and a 'chef' bootstrapper that installs query skills for AI agents, suggesting some agentic tooling, but interaction still requires exact HelixQL syntax or precise JSON request_type payloads (helixdb-docs-8), not free natural-language commands. Multiple hands-on community reports explicitly contradict any natural-language-command capability, calling HelixQL an added 'barrier to entry' that isn't 'AI coding friendly' and asking to 'sidestep the DSL' so LLMs can generate queries more easily (helixdb-comm-1, helixdb-comm-2, helixdb-comm-5, helixdb-comm-10). Missing for 10: evidence of a true NL-to-query interface, first-party benchmarks showing NL command success, and resolution of the DSL-friction complaints.

   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”
   • [claimed-docs] “helix_execute_read_query: execute exact v3 request_type: "read" JSON; requires database.query.read.”
   • [community] “At the moment I wouldn't consider HelixDB because of HelixQL. With OpenCypher even older cheap models can generate queries... by creating He…”
   • [community] “Can I run this as an embedded DB like sqlite? Can I sidestep the DSL? I want my LLMs to generate queries and using a new language is going t…”
   • [community] “our new query language, HelixQL — But why? Why increase the barrier of entry for your system?”
   • [community] “This is very cool, and right up my alley. Hesitant to try it out because of the bespoke query language for now.”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round to HelixDB
   Weaviate—none0/10

   The evidence pack covers client libraries, quickstart guides, and an MCP server, but there is no mention of an interactive API reference (e.g., Swagger/OpenAPI console) with runnable, in-browser examples. missing for 10: interactive API explorer/playground, runnable code snippets embedded in docs, evidence of live query execution from documentation.

   ⚑ flag

   HelixDB~partialprobed4/10

   There's an OpenAPI spec exposed (openapi.json) and a quickstart doc that walks through initializing, running, and stopping a generated query, showing some runnable-example content, but no evidence of an actual interactive API reference UI (e.g., Swagger/Redoc-style 'try it out' explorer) tied to that spec. Missing for 10: evidence of an interactive browsable API reference with embedded runnable/executable examples, not just a static OpenAPI JSON file and CLI quickstart.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.helix-db.com/openapi.json — contains "openapi" key”
   • [claimed-docs] “Initialize HelixDB, start a local instance, run the generated query, and stop it”
   • [probe] “official CLI documented at https://docs.helix-db.com/cli/getting-started”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to HelixDB
   Weaviate—none0/10

   The evidence pack contains no mention of an OpenAPI spec, Swagger docs, or any machine-readable API specification being available for download; it only covers client libraries, MCP server, and quickstart guides. Since Weaviate exposes a REST/GraphQL API, this axis clearly applies to the product category, but no evidence confirms a downloadable spec.

   ⚑ flag

   HelixDB✓fullprobed8/10

   A live probe confirms an OpenAPI spec is served at docs.helix-db.com/openapi.json returning HTTP 200 with an 'openapi' key, plus an llms.txt machine-readable doc endpoint, giving concrete evidence of downloadable machine-readable specs. Missing for 10: no independent/community confirmation of the spec's completeness or usage in the wild, and no first-party doc page explicitly describing/linking the OpenAPI spec as a supported artifact.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.helix-db.com/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.helix-db.com/llms.txt # HelixDB > HelixDB combines a property graph, approximate vector search, an…”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round to HelixDB
   Weaviate~partialclaimed4/10

   Weaviate supports self-hosted local deployments (Docker, Kubernetes) and a free cloud cluster tier, which a user could stand up as an isolated dev/test environment separate from production, and multi-tenancy provides data isolation between tenants. However, there is no explicit documented 'sandbox' feature or guidance for testing against a non-production environment without affecting live data. missing for 10: dedicated sandbox/staging environment documentation, guidance on test-vs-prod separation workflows, independent confirmation that local/free-tier usage is treated as a true sandbox.

   • [github] “You can easily start Weaviate and a local vector embedding model with Docker.”
   • [github] “Weaviate offers multiple installation and deployment options: Docker, Kubernetes, Weaviate Cloud”
   • [claimed-docs] “Always free — 1 cluster per user, upgrade to paid anytime.”
   • [claimed-docs] “Multi-tenancy provides data isolation. Each tenant is stored on a separate shard. Data stored in one tenant is not visible to another tenant…”

   proof ↗⚑ flag

   HelixDB~partialclaimed6/10

   Docs describe running a local/embedded HelixDB instance (quickstart, embedded engine) and a one-shot 'helix chef' bootstrapper that scaffolds a project, starts a local instance, and seeds example data — effectively a local sandbox distinct from any production deployment. Scoped, environment-specific API keys (read-only/read-write) further support separating test vs prod credentials. However, there is no explicit 'sandbox mode' or staging/production isolation feature documented, and no community/hands-on confirmation that this local setup is used specifically to avoid touching production data. Missing for 10: explicit sandbox/staging environment documentation, isolation guarantees between local and prod data, and independent user confirmation of this workflow.

   • [claimed-docs] “Initialize HelixDB, start a local instance, run the generated query, and stop it”
   • [claimed-docs] “Embedded database — run the same engine and queries in process with memory, disk, or object storage.”
   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”
   • [claimed-docs] “Role-based access control. Scoped API keys with read-only, read-write, or operation-restricted permissions for least-privilege credentials p…”

   proof ↗⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Weaviate—none0/10

   No evidence pack item mentions API versioning scheme or a documented deprecation policy for Weaviate's APIs; all evidence covers search, RAG, multi-tenancy, backups, and MCP integration instead. Missing for 10: any mention of API version numbers, changelog/deprecation notices, or a stability/support policy document.

   ⚑ flag

   HelixDB—none0/10

   There is mention of a v3 request model and release notes, but no evidence of a formal API versioning scheme or documented deprecation policy for HelixDB's APIs/SDKs/query language.

   ⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Weaviate
   Weaviate~partialclaimed3/10

   Evidence only shows generic references to 'importing data' and 'creating collections' (e.g., weaviate-docs-5, weaviate-docs-12, weaviate-gh-1) without any explicit mention of a batch/bulk API for importing, updating, or deleting many objects at once. Bulk operations are a standard vector-DB capability, so the axis applies, but the pack lacks concrete documentation of batch size limits, bulk delete, or batch import endpoints. missing for 10: explicit batch import/delete API docs, performance/throughput claims for bulk operations, independent confirmation of bulk operation reliability.

   • [claimed-docs] “Set up a collection - Create a collection and import data into it.”
   • [claimed-docs] “Import objects directly into Weaviate without having to manually specify embeddings”
   • [github] “Weaviate supports two approaches to store vectors: automatic vectorization at import using integrated models ... or direct import of pre-com…”

   proof ↗⚑ flag

   HelixDB—none0/10

   The evidence pack contains no mention of batch/bulk insert, bulk update, or multi-item operation APIs; the closest is a single operation-tree request model (helixdb-docs-6) and ACID transactions (helixdb-docs-9), but neither describes performing operations across many items at once.

   ⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round drawn
   Weaviate—none0/10

   Weaviate is a vector database with search, RAG, multi-tenancy, backup and agent-integration features, but there is no evidence of an event-driven rules/triggers system that automatically fires actions based on defined conditions or data events. The closest mentions (agentic search, Query Agent, MCP server) describe query/retrieval capabilities, not rule-based automation triggers.

   ⚑ flag

   HelixDB—none0/10

   HelixDB is a graph/vector/text database with query and transaction capabilities, but no evidence describes event-driven triggers, rules engines, or automatic actions firing on data events; the evidence pack only covers queries, indexes, SDKs, MCP access, and access control.

   ⚑ flag

3. ai-native userVersion, review, and roll back my automations

   weight 1 · round drawn
   Weaviate—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

   HelixDB—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

Backup

1. platform-engineerBack up collections with snapshots and restore them

   weight 2 · round to Weaviate
   Weaviate✓fullclaimed8/10

   Docs explicitly cover backup/restore functionality including cloud blob storage integration (S3/GCS/Azure), cross-provider restore, incremental backups, and choice of backing up entire instance or selected collections. missing for 10: independent/hands-on corroboration of restore success, detail on snapshot scheduling/automation, and recovery time/consistency guarantees.

   • [claimed-docs] “Seamless integration with widely-used cloud blob storage, such as AWS S3, GCS, or Azure Storage”
   • [claimed-docs] “Backup and Restore between different storage providers”
   • [claimed-docs] “Incremental backups that only store changed data, reducing backup and speeding up backup times”
   • [claimed-docs] “Choice of backing up an entire instance, or selected collections only”

   proof ↗⚑ flag

   HelixDB—none0/10

   No evidence of any backup/snapshot or restore capability for collections; docs cover embedded storage, indexes, transactions, RBAC, and multi-tenancy but never mention backup or restore workflows. missing for 10: any documentation of snapshot creation, backup scheduling, or restore procedures.

   ⚑ flag

Freshness

1. developerUpsert and delete records continuously and have changes reflected in search results quickly, with documented freshness/consistency behavior

   weight 2 · round drawn
   Weaviate~partialclaimed3/10

   Docs confirm CRUD-style data import and replication factor settings (weaviate-docs-9/17) but there is no explicit documentation of freshness/consistency guarantees after upsert/delete, nor any consistency-level or read-after-write behavior described in the evidence pack. missing for 10: documented consistency levels/tunable consistency, read-after-write freshness guarantees, benchmarks or docs on indexing latency for updates/deletes.

   • [claimed-docs] “Weaviate allows data replication across a multi-node cluster by setting a replication factor > 1. This enables a variety of benefits such as…”
   • [claimed-docs] “Weaviate allows data replication across a multi-node cluster by setting a replication factor > 1.”
   • [claimed-docs] “Set up a collection - Create a collection and import data into it.”

   proof ↗⚑ flag

   HelixDB~partialclaimed3/10

   Docs claim ACID transactions across graph, vector, and text data in a single transaction, implying consistent updates, and search/filtering across nodes and edges, but there is no explicit documentation of upsert/delete operations or freshness/consistency guarantees for how quickly search results reflect changes. Missing for 10: explicit upsert/delete API documentation, documented latency/consistency model for index updates, and independent verification of update-to-search-visibility timing.

   • [claimed-docs] “ACID transactions across graph, vector, and text data in a single transaction.”
   • [claimed-docs] “Search and filtering on both nodes and edges, not just nodes.”
   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”
   • [claimed-docs] “Text indexes provide durable BM25 search over string properties on nodes or edges.”

   proof ↗⚑ flag

Portability

1. developerBulk-import and bulk-export vectors plus metadata in documented formats

   weight 2 · round to Weaviate
   Weaviate~partialclaimed6/10

   Bulk import of objects with either auto-vectorization or pre-computed vector embeddings is well documented (weaviate-docs-12, -15, -24, -28, weaviate-gh-1), and client libraries support this at scale. Export-side evidence is limited to backup/restore to cloud blob storage (S3/GCS/Azure) with incremental and selective backups (weaviate-docs-10, -11, -18, -19), which covers whole-instance/collection portability but is not explicitly documented as a per-object bulk vector+metadata export format (e.g., CSV/JSON dump) for developer-level data lifecycle use. Missing for 10: explicit documented bulk-export API/format for vectors+metadata (vs. binary backup snapshots), and independent/hands-on confirmation of round-trip import/export fidelity.

   • [claimed-docs] “Import objects directly into Weaviate without having to manually specify embeddings”
   • [claimed-docs] “Import objects and vectorize them with the Weaviate Embeddings service. ](/weaviate/quickstart?import=vectorization#create-a-collection)[ …”
   • [claimed-docs] “Import objects and vectorize them with the Weaviate Embeddings service. Import pre-computed vector embeddings along with your data.”
   • [claimed-docs] “Import vectors: Import pre-computed vector embeddings along with your data.”
   • [github] “Weaviate supports two approaches to store vectors: automatic vectorization at import using integrated models ... or direct import of pre-com…”
   • [claimed-docs] “Seamless integration with widely-used cloud blob storage, such as AWS S3, GCS, or Azure Storage”
   • [claimed-docs] “Backup and Restore between different storage providers”
   • [claimed-docs] “Incremental backups that only store changed data, reducing backup and speeding up backup times”
   • [claimed-docs] “Choice of backing up an entire instance, or selected collections only”

   proof ↗⚑ flag

   HelixDB—none0/10

   No evidence of a documented bulk-import/export mechanism for vectors and metadata in specific formats; docs cover vector indexes, transactions, and query capabilities but not batch load/dump tooling or file formats. missing for 10: bulk import/export commands or APIs, documented file formats (e.g. CSV/Parquet/JSON), and any example or CLI reference for data migration.

   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”
   • [claimed-docs] “ACID transactions across graph, vector, and text data in a single transaction.”
   • [claimed-docs] “Database-specific overrides can change the sustained rate, burst capacity, and query attempt budget.”

   proof ↗⚑ flag

Local dev

1. developerRun the database embedded in-process or as a lightweight local instance for development and small workloads

   weight 2 · round to HelixDB
   Weaviate~partialcommunity5/10

   Weaviate is well documented for lightweight local deployment via Docker (weaviate-gh-2, weaviate-gh-3), and a community report confirms an embedded Python package mode exists as an alternative to running a separate process (weaviate-comm-1), but the evidence pack contains no first-party documentation describing or supporting embedded in-process operation as an official deployment mode. Missing for 10: first-party docs on embedded mode, language coverage beyond Python, and guidance on limitations of embedded/local instances for production-like dev workloads.

   • [github] “You can easily start Weaviate and a local vector embedding model with Docker.”
   • [github] “Weaviate offers multiple installation and deployment options: Docker, Kubernetes, Weaviate Cloud”
   • [community] “Weaviate is pretty cool IMO. It is open source and fairly easy to get running locally... You can even run Weaviate as an embedded python pac…”

   proof ↗⚑ flag

   HelixDB✓fullcommunity8/10

   First-party docs explicitly describe an embedded mode ("run the same engine and queries in process with memory, disk, or object storage") and a quickstart/CLI flow for starting and stopping a local instance for development, corroborated by the helix chef bootstrapper that scaffolds and starts a local instance. Missing for 10: independent/hands-on confirmation that embedded mode works as described, and a direct answer to the community question about running it like an embedded SQLite-style DB.

   • [claimed-docs] “Initialize HelixDB, start a local instance, run the generated query, and stop it”
   • [claimed-docs] “Embedded database — run the same engine and queries in process with memory, disk, or object storage.”
   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”
   • [community] “Can I run this as an embedded DB like sqlite? Can I sidestep the DSL? I want my LLMs to generate queries and using a new language is going t…”

   proof ↗⚑ flag

Managed cloud

1. developerUse a fully managed cloud version of the database with programmatic provisioning

   weight 2 · round drawn
   Weaviate~partialclaimed5/10

   Evidence confirms a fully managed offering (Weaviate Cloud) with a free tier and upgrade path, and lists Weaviate Cloud as one of the deployment options alongside Docker/Kubernetes, but there is no documentation of a provisioning API, CLI, or Terraform-style IaC tool for creating/managing cloud clusters programmatically. Missing for 10: explicit programmatic provisioning API/CLI/IaC support, independent confirmation of automated cluster creation workflows.

   • [claimed-docs] “Always free — 1 cluster per user, upgrade to paid anytime.”
   • [github] “Weaviate offers multiple installation and deployment options: Docker, Kubernetes, Weaviate Cloud”
   • [claimed-docs] “Follow the instructions below to install one of the official client libraries, available in Python, JavaScript/TypeScript, Go, and Java.”

   proof ↗⚑ flag

   HelixDB~partialprobed5/10

   Helix Cloud is documented as a real managed offering with multi-tenancy, RBAC/API keys, and configurable rate limits, and a CLI plus OpenAPI spec exist, implying some programmatic control-plane surface. However there is no explicit documentation of an API/CLI command dedicated to provisioning or spinning up new cloud database instances programmatically, and community threads note pricing (~$600/mo) without confirming a self-serve programmatic provisioning flow. Missing for 10: explicit provisioning API/CLI examples (create/delete/scale a Helix Cloud instance), infra-as-code (e.g. Terraform) support, and independent confirmation of automated provisioning working end-to-end.

   • [claimed-docs] “Helix Cloud focuses on row-level isolation, which lets you implement any tenancy model at the application layer without structural constrain…”
   • [claimed-docs] “Role-based access control. Scoped API keys with read-only, read-write, or operation-restricted permissions for least-privilege credentials p…”
   • [claimed-docs] “Database-specific overrides can change the sustained rate, burst capacity, and query attempt budget.”
   • [probe] “official CLI documented at https://docs.helix-db.com/cli/getting-started”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.helix-db.com/openapi.json — contains "openapi" key”
   • [community] “can you host this yourself or do you need to use helix-cloud? ... it looks like that starts at like $600/mo which is above my experimentatio…”

   proof ↗⚑ flag

Self managed

1. platform-engineerDeploy to production on Kubernetes with an official Helm chart or operator

   weight 1 · round to Weaviate
   Weaviate~partialclaimed4/10

   Evidence confirms Kubernetes is a supported deployment option (weaviate-gh-3), which implies K8s-native deployment tooling exists, but no citation explicitly mentions an official Helm chart or Kubernetes operator. Missing for 10: explicit documentation of the Helm chart repo, operator CRDs, or production-grade K8s deployment guide.

   • [github] “Weaviate offers multiple installation and deployment options: Docker, Kubernetes, Weaviate Cloud”

   proof ↗⚑ flag

   HelixDB—none0/10

   No evidence of a Helm chart, Kubernetes operator, or any Kubernetes-specific deployment guidance; the evidence pack only covers local/embedded quickstart, Helix Cloud (managed multi-tenant), CLI, and MCP setup. Community threads even question self-hosting options versus Helix Cloud, with no mention of K8s tooling.

   • [claimed-docs] “Initialize HelixDB, start a local instance, run the generated query, and stop it”
   • [claimed-docs] “Embedded database — run the same engine and queries in process with memory, disk, or object storage.”
   • [community] “can you host this yourself or do you need to use helix-cloud? ... it looks like that starts at like $600/mo which is above my experimentatio…”
   • [probe] “official CLI documented at https://docs.helix-db.com/cli/getting-started”

   proof ↗⚑ flag

Embeddings

1. ml-engineerHave the database generate embeddings at ingest and query time using built-in or configured model providers, instead of running a separate embedding pipeline

   weight 3 · round to Weaviate
   Weaviate✓fullclaimed8/10

   Weaviate documents built-in vectorization at import (automatic vectorization via integrated models, including its own Embeddings service) and integration with many self-hosted/API model providers, avoiding a separate embedding pipeline; it also supports natural-language query-time search that uses these configured providers. Missing for 10: independent hands-on verification of query-time embedding generation quality/reliability and broader corroboration beyond vendor docs.

   • [claimed-docs] “Import objects directly into Weaviate without having to manually specify embeddings”
   • [claimed-docs] “Import objects and vectorize them with the Weaviate Embeddings service. ](/weaviate/quickstart?import=vectorization#create-a-collection)[ …”
   • [claimed-docs] “Weaviate integrates with a variety of self-hosted and API-based models from a range of providers.”
   • [github] “Weaviate supports two approaches to store vectors: automatic vectorization at import using integrated models ... or direct import of pre-com…”
   • [github] “You can easily start Weaviate and a local vector embedding model with Docker.”
   • [claimed-docs] “Import objects and vectorize them with the Weaviate Embeddings service. Import pre-computed vector embeddings along with your data.”

   proof ↗⚑ flag

   HelixDB—none0/10

   Evidence shows vector indexes for storing and ranking embeddings, but there is no mention of built-in embedding generation or configurable model providers at ingest/query time — users still appear to supply vectors themselves. missing for 10: any documentation of built-in embedding generation, model provider configuration, or automatic text-to-vector conversion at ingest/query time.

   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”
   • [claimed-docs] “ACID transactions across graph, vector, and text data in a single transaction.”
   • [claimed-docs] “Search and filtering on both nodes and edges, not just nodes.”

   proof ↗⚑ flag

Filtering

1. developerFilter vector search by structured metadata conditions without wrecking recall or latency

   weight 3 · round to HelixDB
   Weaviate~partialprobed3/10

   Evidence only hints at filtering capability via 'keyword filtering' combined with vector search (weaviate-gh-4) and mentions of inverted indexes for structured data (weaviate-probe-1), but there is no documentation addressing how structured metadata filters interact with vector search to preserve recall or latency. missing for 10: explicit docs on pre-filtering/post-filtering strategy, benchmarks or claims about recall/latency impact of combined filter+vector queries, and independent corroboration of filter performance.

   • [github] “It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.weaviate.io/llms.txt # Weaviate ## TL;DR Weaviate is an open-source vector database (Go) that sto…”

   proof ↗⚑ flag

   HelixDB~partialcommunity6/10

   Docs explicitly describe pre-filtering an exact candidate set via graph traversal before vector ranking, plus vector indexes with distance metrics, search/filtering on nodes and edges, and text/BM25 indexes that can combine with vector search — supporting metadata-constrained vector search. However there is no benchmark or independent evidence quantifying recall/latency impact of filtering, and community comments raise concerns about performance on multi-hop queries and small benchmark datasets, which is adjacent but not a direct contradiction of filtered-vector-search quality. missing for 10: quantified recall/latency benchmarks specifically for filtered vector search, independent hands-on validation that filtering doesn't degrade recall/latency.

   • [claimed-docs] “traverse and filter an exact candidate set before vector ranking, so results cannot escape graph or permission boundaries.”
   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”
   • [claimed-docs] “Search and filtering on both nodes and edges, not just nodes.”
   • [claimed-docs] “Text indexes provide durable BM25 search over string properties on nodes or edges.”
   • [community] “We've been having some issues with intermittent performance on multi hop queries. What's your p99 like for multi hops?”
   • [community] “page says your benchmark runs on 5M of records only. Is it incredibly small dataset in current world... count(*) query having 5s latency on …”

   proof ↗⚑ flag

2. developerExpress rich filter conditions (ranges, geo, nested boolean logic, array membership) in queries

   weight 2 · round drawn
   Weaviate—none0/10

   The evidence pack covers hybrid search, RAG, multi-tenancy, replication, backups, and model integrations, but contains no mention of Weaviate's filter operators (e.g., range, GeoRange, nested And/Or, ContainsAny/ContainsAll for arrays) despite these being real, documented Weaviate capabilities. Without citations describing filter syntax or examples, this story cannot be credited as delivered from this evidence pack alone.

   ⚑ flag

   HelixDB—none0/10

   Docs mention generic 'search and filtering on nodes and edges' and vector/text indexes, but there is no evidence of range queries, geo filters, nested boolean logic, or array-membership filtering in HelixQL. missing for 10: range filter examples, geo/spatial filter support, nested AND/OR/NOT boolean composition, array/IN membership filters.

   • [claimed-docs] “Search and filtering on both nodes and edges, not just nodes.”
   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”
   • [claimed-docs] “Text indexes provide durable BM25 search over string properties on nodes or edges.”

   proof ↗⚑ flag

Scaling

1. platform-engineerScale beyond one node with sharding or distributed deployment

   weight 2 · round to Weaviate
   Weaviate✓fullclaimed8/10

   Docs confirm multi-node distributed deployment with replication factor >1 for high availability, sharding via multi-tenancy (each tenant on a separate shard), and multiple deployment options including Kubernetes for cluster scaling. First-party documentation is strong but lacks independent hands-on validation of multi-node scaling specifically. Missing for 10: independent/community corroboration of production multi-node cluster scaling behavior, benchmarks on distributed performance.

   • [claimed-docs] “Multi-tenancy provides data isolation. Each tenant is stored on a separate shard. Data stored in one tenant is not visible to another tenant…”
   • [claimed-docs] “Weaviate allows data replication across a multi-node cluster by setting a replication factor > 1. This enables a variety of benefits such as…”
   • [claimed-docs] “Weaviate allows data replication across a multi-node cluster by setting a replication factor > 1.”
   • [github] “Weaviate offers multiple installation and deployment options: Docker, Kubernetes, Weaviate Cloud”

   proof ↗⚑ flag

   HelixDB—none0/10

   No evidence of sharding, clustering, or distributed multi-node deployment; docs focus on embedded/single-instance database and Helix Cloud's row-level multi-tenancy at the application layer, not horizontal scaling across nodes. Community threads even question source availability and self-hosting scale, but nothing confirms distributed/sharded architecture.

   • [claimed-docs] “Embedded database — run the same engine and queries in process with memory, disk, or object storage.”
   • [claimed-docs] “Helix Cloud focuses on row-level isolation, which lets you implement any tenancy model at the application layer without structural constrain…”
   • [community] “Where's the source code for the database itself? Looks like the repo is just a client.”
   • [community] “page says your benchmark runs on 5M of records only. Is it incredibly small dataset in current world... count(*) query having 5s latency on …”

   proof ↗⚑ flag

2. platform-engineerReplicate data across nodes or zones for high availability with a documented consistency model

   weight 2 · round to Weaviate
   Weaviate~partialclaimed5/10

   Docs confirm Weaviate replicates data across multi-node clusters via a replication factor >1 for high availability, but the evidence pack does not cite specifics of a documented consistency model (e.g., tunable consistency levels, quorum reads/writes) beyond the general HA claim. Missing for 10: explicit documentation of consistency levels/tunable consistency, cross-zone replication guarantees, and independent verification of HA behavior in production.

   • [claimed-docs] “Weaviate allows data replication across a multi-node cluster by setting a replication factor > 1. This enables a variety of benefits such as…”
   • [claimed-docs] “Weaviate allows data replication across a multi-node cluster by setting a replication factor > 1.”

   proof ↗⚑ flag

   HelixDB—none0/10

   No evidence of any replication, multi-node clustering, or documented consistency model; docs mention row-level tenancy isolation and RBAC but nothing about cross-node/zone replication or HA guarantees. missing for 10: replication architecture, multi-zone/multi-node deployment topology, consistency model documentation (e.g., CP/AP tradeoffs), failover/HA guarantees.

   • [claimed-docs] “Helix Cloud focuses on row-level isolation, which lets you implement any tenancy model at the application layer without structural constrain…”
   • [claimed-docs] “Role-based access control. Scoped API keys with read-only, read-write, or operation-restricted permissions for least-privilege credentials p…”

   proof ↗⚑ flag

Tenancy

1. platform-engineerEnforce granular access control (API keys, roles, per-collection permissions) on database operations

   weight 2 · round to HelixDB
   Weaviate—none0/10

   The evidence pack covers multi-tenancy data isolation, replication, and backups but contains no mention of API keys, RBAC, roles, or per-collection permission enforcement — an applicable but unevidenced capability for a platform-engineer persona.

   ⚑ flag

   HelixDB~partialclaimed6/10

   Docs confirm scoped API keys with read-only/read-write/operation-restricted roles and least-privilege credentials per service/environment (helixdb-docs-11), plus row-level isolation for tenancy (helixdb-docs-7) and per-database rate/limit overrides (helixdb-docs-13). However, there's no evidence of true per-collection (per-node-type/index) permission scoping — isolation is described at row-level/application-layer, not as fine-grained collection ACLs, and no independent/hands-on confirmation exists. Missing for 10: explicit per-collection/per-schema-object permission granularity, independent validation of RBAC enforcement in production.

   • [claimed-docs] “Role-based access control. Scoped API keys with read-only, read-write, or operation-restricted permissions for least-privilege credentials p…”
   • [claimed-docs] “Helix Cloud focuses on row-level isolation, which lets you implement any tenancy model at the application layer without structural constrain…”
   • [claimed-docs] “Database-specific overrides can change the sustained rate, burst capacity, and query attempt budget.”

   proof ↗⚑ flag

2. platform-engineerIsolate many tenants cheaply using namespaces, partitions, or per-tenant collections with documented limits

   weight 3 · round to Weaviate
   Weaviate~partialclaimed6/10

   Docs confirm per-tenant isolation via separate shards, auto-tenant creation, and replication for HA, which directly supports cheap multi-tenant isolation via per-tenant collections/shards (weaviate-docs-7, weaviate-docs-8, weaviate-docs-16, weaviate-docs-9, weaviate-docs-17). However, no evidence cites concrete documented limits (e.g., max tenants per node/cluster, cost/scale ceilings) that a platform engineer would need to plan capacity. missing for 10: explicit documented tenant-count limits or scaling guidance, independent benchmarks/case studies of large tenant counts.

   • [claimed-docs] “Multi-tenancy provides data isolation. Each tenant is stored on a separate shard. Data stored in one tenant is not visible to another tenant…”
   • [claimed-docs] “To change this behavior so Weaviate creates a new tenant, set `autoTenantCreation` to `true` in the collection definition.”
   • [claimed-docs] “By default, Weaviate returns an error if you try to insert an object into a non-existent tenant. To change this behavior so Weaviate creates…”
   • [claimed-docs] “Weaviate allows data replication across a multi-node cluster by setting a replication factor > 1. This enables a variety of benefits such as…”
   • [claimed-docs] “Weaviate allows data replication across a multi-node cluster by setting a replication factor > 1.”

   proof ↗⚑ flag

   HelixDB~partialclaimed3/10

   Helix Cloud docs describe only row-level isolation implemented at the application layer, explicitly noting 'no structural constraints on the database' rather than native namespaces, partitions, or per-tenant collections; RBAC/scoped API keys and rate-limit overrides exist but are not tied to a documented per-tenant isolation model with limits. missing for 10: native namespace/partition/collection-based tenant isolation, documented per-tenant resource limits, and any benchmark or case study showing cheap multi-tenant scaling.

   • [claimed-docs] “Helix Cloud focuses on row-level isolation, which lets you implement any tenancy model at the application layer without structural constrain…”
   • [claimed-docs] “Role-based access control. Scoped API keys with read-only, read-write, or operation-restricted permissions for least-privilege credentials p…”
   • [claimed-docs] “Database-specific overrides can change the sustained rate, burst capacity, and query attempt budget.”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round drawn
   Weaviate—none0/10

   The evidence pack documents Weaviate's API/client libraries, hybrid search, RAG, and MCP server, but never compares API capabilities against a separate UI (e.g., Weaviate Cloud console) or claims feature parity between the two. Missing for 10: any explicit statement or example that every UI-console action (e.g., cluster management, monitoring, schema editing) can be replicated via the REST/GraphQL/gRPC API, and any independent confirmation of this parity.

   ⚑ flag

   HelixDB—none0/10

   The evidence pack documents SDKs, CLI, MCP server, and OpenAPI spec but never describes a HelixDB UI/console or compares its feature set against the API, so there's no basis to confirm API-UI parity. missing for 10: any description of a HelixDB web console/UI feature set, and evidence that all such features are also exposed via API/CLI/SDK.

   ⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to Weaviate
   Weaviate~partialcommunity5/10

   Weaviate offers backup/restore across cloud storage providers and open client libraries (Python/JS/Go/Java) that could be used to pull data out, and the product itself is open-source, supporting a 'leave without lock-in' narrative. However there is no explicit documentation of a bulk data export feature or open interchange format (e.g., JSON/parquet dump) — backups are described as instance restores rather than portable exports. Missing for 10: explicit bulk-export/dump-to-open-format documentation, evidence of exporting vectors+metadata in a standard interchange format, and independent confirmation of successful full-data migration out of Weaviate.

   • [claimed-docs] “Seamless integration with widely-used cloud blob storage, such as AWS S3, GCS, or Azure Storage”
   • [claimed-docs] “Backup and Restore between different storage providers”
   • [claimed-docs] “Incremental backups that only store changed data, reducing backup and speeding up backup times”
   • [claimed-docs] “Choice of backing up an entire instance, or selected collections only”
   • [claimed-docs] “Follow the instructions below to install one of the official client libraries, available in Python, JavaScript/TypeScript, Go, and Java.”
   • [community] “Weaviate is pretty cool IMO. It is open source and fairly easy to get running locally... You can even run Weaviate as an embedded python pac…”

   proof ↗⚑ flag

   HelixDB—none0/10

   While HelixDB is Apache 2.0 open source (helixdb-docs-12) and can run embedded/self-hosted (helixdb-docs-2), there is no evidence of an explicit data export/migration tool or open-format data dump capability, and community comments explicitly raise vendor lock-in concerns about the bespoke query language (helixdb-comm-3, helixdb-comm-8) with no rebuttal shown for data portability.

   • [claimed-docs] “Open source: Apache 2.0 licensed and developed in the open on GitHub.”
   • [claimed-docs] “Embedded database — run the same engine and queries in process with memory, disk, or object storage.”
   • [community] “> so much easier that it's worth a bit of a learning curve — I think you misspelled 'vendor lock in'”
   • [community] “can you host this yourself or do you need to use helix-cloud? ... it looks like that starts at like $600/mo which is above my experimentatio…”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to Weaviate
   Weaviate✓fullprobed7/10

   Weaviate's GitHub repo and docs explicitly describe it as an open-source vector database, and a community comment independently corroborates that it is open source and can be run locally. missing for 10: explicit citation of the specific open-source license name (e.g., BSD-3-Clause) and confirmation that the full source (not just parts) is publicly available under that license.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.weaviate.io/llms.txt # Weaviate ## TL;DR Weaviate is an open-source vector database (Go) that sto…”
   • [community] “Weaviate is pretty cool IMO. It is open source and fairly easy to get running locally... You can even run Weaviate as an embedded python pac…”
   • [github] “Weaviate offers multiple installation and deployment options: Docker, Kubernetes, Weaviate Cloud”

   proof ↗⚑ flag

   HelixDB!disputedcontradicted4/10

   HelixDB's docs and site state it is Apache 2.0 licensed and developed in the open on GitHub, with a public repo. However, a firsthand community report explicitly questions this, noting 'Where's the source code for the database itself? Looks like the repo is just a client,' suggesting the core engine may not be fully open despite the license claim. missing for 10: a rebuttal or confirmation that the full database engine (not just client/SDK code) is in the public repo, and independent verification of build-from-source for the core engine.

   • [claimed-docs] “Open source: Apache 2.0 licensed and developed in the open on GitHub.”
   • [github] “helix chef is an interactive, one-shot bootstrapper. It installs the HelixDB query skills and docs MCP, scaffolds a project, starts a local …”
   • [community] “Where's the source code for the database itself? Looks like the repo is just a client.”

   proof ↗⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round to Weaviate
   Weaviate✓fullprobed9/10

   Weaviate is explicitly open-source (Go) and offers self-hosted deployment via Docker/Kubernetes in addition to Weaviate Cloud, with community confirmation of easy local/self-hosted setup including an embedded mode. Missing for 10: no independent audit of self-hosted feature parity with the managed cloud offering (some features like Query Agent are noted cloud-only).

   • [github] “Weaviate offers multiple installation and deployment options: Docker, Kubernetes, Weaviate Cloud”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.weaviate.io/llms.txt # Weaviate ## TL;DR Weaviate is an open-source vector database (Go) that sto…”
   • [community] “Weaviate is pretty cool IMO. It is open source and fairly easy to get running locally... You can even run Weaviate as an embedded python pac…”
   • [claimed-docs] “Get answers from your data by using a natural language prompt/question. Cloud only”
   • [github] “You can easily start Weaviate and a local vector embedding model with Docker.”

   proof ↗⚑ flag

   HelixDB✓fullcommunity8/10

   HelixDB docs show a working local self-host quickstart, an embedded-database mode (memory/disk/object storage), and Apache-2.0 open-source licensing, directly supporting self-hosting the core engine. Community skepticism (e.g., asking whether the public repo is 'just a client') raises an open question but is not a confirmed hands-on failure, so it tempers confidence rather than the verdict. Missing for 10: independent third-party confirmation that a self-hosted instance matches Helix Cloud's full feature set, and clarification of the 'is the core engine actually in the repo' community question.

   • [claimed-docs] “Initialize HelixDB, start a local instance, run the generated query, and stop it”
   • [claimed-docs] “Embedded database — run the same engine and queries in process with memory, disk, or object storage.”
   • [claimed-docs] “Open source: Apache 2.0 licensed and developed in the open on GitHub.”
   • [community] “Where's the source code for the database itself? Looks like the repo is just a client.”
   • [community] “can you host this yourself or do you need to use helix-cloud? ... it looks like that starts at like $600/mo which is above my experimentatio…”

   proof ↗⚑ flag

Benchmarks

1. platform-engineerSee published benchmarks or measured latency/recall numbers backing the database's performance claims

   weight 2 · round drawn
   Weaviate—none0/10

   No evidence pack items contain published benchmarks, latency numbers, recall metrics, or any quantitative performance comparisons; the docs focus on feature descriptions (hybrid search, multi-tenancy, backups, replication) without measured performance data. missing for 10: benchmark reports, latency/recall figures, third-party performance evaluations.

   ⚑ flag

   HelixDB—none0/10

   The evidence pack contains no first-party (claimed-docs) benchmark tables, latency, or recall numbers for HelixDB; the only performance data referenced comes from community discussion (e.g., a mention of a benchmark page running on 5M records with 5s count(*) latency, and unanswered questions about p99 multi-hop latency), which is not corroborated by any vendor-tier documentation in this pack. Because disputed verdicts require citations from two distinct tiers and only community-tier evidence exists here, this axis cannot be marked disputed and instead shows no vendor-backed performance evidence. missing for 10: published first-party benchmark methodology, latency percentiles (p50/p95/p99), recall metrics for vector/BM25 search, and independent reproduction of any performance claims.

   • [community] “We've been having some issues with intermittent performance on multi hop queries. What's your p99 like for multi hops?”
   • [community] “page says your benchmark runs on 5M of records only. Is it incredibly small dataset in current world... count(*) query having 5s latency on …”

   proof ↗⚑ flag

Index tuning

1. ml-engineerTune index parameters (HNSW graph settings, index types) to trade recall against latency and memory

   weight 2 · round drawn
   Weaviate—none0/10

   The evidence pack contains no mention of HNSW parameters (ef, efConstruction, maxConnections), index type selection (flat vs HNSW vs dynamic), or any recall/latency/memory tuning guidance — only general search, multi-tenancy, replication, and backup features are covered. Missing for 10: any documentation of HNSW graph parameter configuration, index type trade-off guidance, or benchmarks showing recall/latency/memory tuning.

   ⚑ flag

   HelixDB—none0/10

   Docs mention that vector indexes require a dimension and distance metric, but there is no evidence of exposing HNSW-specific tuning knobs (e.g., M, ef_construction, ef_search) or alternative index types that would let an ml-engineer trade recall against latency/memory. Community threads even raise unresolved performance concerns on multi-hop queries with no mention of tunable index parameters.

   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”
   • [community] “We've been having some issues with intermittent performance on multi hop queries. What's your p99 like for multi hops?”
   • [community] “page says your benchmark runs on 5M of records only. Is it incredibly small dataset in current world... count(*) query having 5s latency on …”

   proof ↗⚑ flag

2. ml-engineerEnable vector quantization or compression to cut memory and storage cost with a documented accuracy trade-off

   weight 2 · round drawn
   Weaviate—none0/10

   The evidence pack contains no mention of vector quantization (PQ, BQ, SQ) or compression features, nor any documented accuracy/memory trade-offs, despite Weaviate actually shipping such features in reality; based solely on this evidence pack, there is no support. Missing for 10: any mention of quantization/compression config options, memory/storage savings benchmarks, or documented recall/accuracy trade-off data.

   ⚑ flag

   HelixDB—none0/10

   Evidence covers vector indexes (dimension/distance metric) but nowhere mentions quantization, compression, or any documented accuracy/memory trade-off; no evidence of such a feature existing. missing for 10: quantization/compression feature docs, memory/storage savings data, accuracy trade-off benchmarks.

   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”

   proof ↗⚑ flag

Pricing

1. developerPrototype on a meaningful free tier before paying anything

   weight 1 · round drawn
   Weaviate~partialclaimed5/10

   Weaviate Cloud offers an 'Always free' 1 cluster tier per user that upgrades to paid anytime, which supports prototyping without payment. However, evidence doesn't detail the free tier's resource limits, duration, or whether it's sufficient for meaningful real-world prototyping, and self-hosted open-source use (free but requiring infra) is a separate path not tied to this pricing claim. missing for 10: details on free tier limits/quotas, independent user confirmation of the free tier being 'meaningful' for real prototyping, comparison to competitor free tiers.

   • [claimed-docs] “Always free — 1 cluster per user, upgrade to paid anytime.”

   proof ↗⚑ flag

   HelixDB~partialcommunity5/10

   HelixDB is Apache 2.0 open source and can be run locally/embedded entirely free for prototyping (helixdb-docs-12, helixdb-docs-1, helixdb-docs-2), satisfying the 'free before paying' story via self-hosting. However, for the managed Helix Cloud offering there is no documented free tier, and a community report states cloud pricing starts around $600/mo, well above an experimentation budget (helixdb-comm-8), contradicting a 'meaningful free tier' for the hosted product path. missing for 10: an explicit low/no-cost Helix Cloud tier, first-party pricing page confirming free-tier limits, and evidence rebutting the $600/mo complaint.

   • [claimed-docs] “Open source: Apache 2.0 licensed and developed in the open on GitHub.”
   • [claimed-docs] “Initialize HelixDB, start a local instance, run the generated query, and stop it”
   • [claimed-docs] “Embedded database — run the same engine and queries in process with memory, disk, or object storage.”
   • [community] “can you host this yourself or do you need to use helix-cloud? ... it looks like that starts at like $600/mo which is above my experimentatio…”
   • [claimed-docs] “Database-specific overrides can change the sustained rate, burst capacity, and query attempt budget.”

   proof ↗⚑ flag

2. developerPay serverless usage-based pricing with transparent per-unit costs instead of provisioning fixed clusters

   weight 2 · round drawn
   Weaviate—none0/10

   The only pricing evidence describes a free tier as '1 cluster per user, upgrade to paid anytime,' implying cluster-based provisioning rather than serverless usage-based per-unit billing; no evidence of transparent per-unit consumption pricing is present.

   • [claimed-docs] “Always free — 1 cluster per user, upgrade to paid anytime.”

   proof ↗⚑ flag

   HelixDB—none0/10

   No evidence in the pack shows HelixDB offering serverless, usage-based, per-unit transparent pricing; the only pricing signal is a community report that Helix Cloud 'starts at like $600/mo' — suggesting a flat/tiered plan rather than metered usage-based billing. Rate-limit docs (sustained rate, burst capacity) describe throttling, not a pricing model.

   • [community] “can you host this yourself or do you need to use helix-cloud? ... it looks like that starts at like $600/mo which is above my experimentatio…”
   • [claimed-docs] “Database-specific overrides can change the sustained rate, burst capacity, and query attempt budget.”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round to Weaviate
   Weaviate~partialclaimed3/10

   Weaviate can be self-hosted via Docker/Kubernetes or run in Weaviate Cloud, which implicitly gives users control over where their data physically resides, but there is no explicit documentation of region-selection or data-residency features for Weaviate Cloud. missing for 10: explicit region/data-residency configuration options, compliance certifications (e.g., GDPR region pinning), and any documentation on choosing a cloud region for hosted deployments.

   • [github] “Weaviate offers multiple installation and deployment options: Docker, Kubernetes, Weaviate Cloud”

   proof ↗⚑ flag

   HelixDB—none0/10

   HelixDB can be self-hosted or embedded (giving implicit control over data location), but there is no evidence of an explicit region/residency selection feature for Helix Cloud or any documented data-residency controls. missing for 10: explicit region selection options, data residency guarantees/documentation, compliance certifications tied to geography.

   • [claimed-docs] “Embedded database — run the same engine and queries in process with memory, disk, or object storage.”
   • [claimed-docs] “Helix Cloud focuses on row-level isolation, which lets you implement any tenancy model at the application layer without structural constrain…”

   proof ↗⚑ flag

2. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Weaviate—none0/10

   The evidence pack covers hybrid search, RAG, multi-tenancy, replication, and backups, but contains no documentation of object/collection deletion APIs, TTL-based expiration, or data retention policies that would let an AI-native user control how long data persists or ensure deletion. Multi-tenancy (isolation) and backups (durability) are adjacent but do not address retention/deletion controls.

   • [claimed-docs] “Multi-tenancy provides data isolation. Each tenant is stored on a separate shard. Data stored in one tenant is not visible to another tenant…”
   • [claimed-docs] “Weaviate allows data replication across a multi-node cluster by setting a replication factor > 1. This enables a variety of benefits such as…”
   • [claimed-docs] “Seamless integration with widely-used cloud blob storage, such as AWS S3, GCS, or Azure Storage”

   proof ↗⚑ flag

   HelixDB—none0/10

   No evidence pack items address data retention policies, deletion controls, TTL/expiry, or user-initiated data purge; documentation covers RBAC, multi-tenancy, and query features but nothing about retention/deletion controls for AI-native users.

   ⚑ flag

3. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Weaviate—none0/10

   No evidence pack item mentions telemetry, usage tracking, opt-out settings, or privacy configuration options for Weaviate; the axis applies to any self-hostable database product but no supporting documentation is provided.

   ⚑ flag

   HelixDB—none0/10

   No evidence pack item mentions telemetry, usage analytics, or an opt-out setting for HelixDB; the docs cover open-source licensing, security, and MCP but not data collection practices. missing for 10: any mention of telemetry collection, opt-out flags/env vars, or privacy policy addressing usage tracking.

   ⚑ flag

Integrations

1. ml-engineerPlug the database into RAG and agent frameworks (LangChain, LlamaIndex, etc.) through maintained first-class integrations

   weight 2 · round to Weaviate
   Weaviate~partialcommunity4/10

   Evidence confirms Weaviate is usable as a RAG backend with official client libraries and an MCP server, and a community report shows it being used with a LangChain retriever (WeaviateHybridSearchRetriever) in practice, but that same report flags a concrete functional gap (can't get it to work asynchronously). There is no first-party documentation in the pack of maintained LangChain/LlamaIndex integration pages, and LlamaIndex is not mentioned at all. Missing for 10: official docs/changelog for LangChain and LlamaIndex integrations, confirmation the async issue is resolved, and any first-party integration-maintenance statement.

   • [claimed-docs] “Weaviate can serve as a robust backend for RAG workflows, where vector search is used to retrieve context that enhances the output of genera…”
   • [claimed-docs] “These agents can leverage semantic insights to make decisions or trigger actions based on the data stored in Weaviate.”
   • [claimed-docs] “Follow the instructions below to install one of the official client libraries, available in Python, JavaScript/TypeScript, Go, and Java.”
   • [community] “Just migrated from Supabase + pgvector to Weaviate hoping to take advantage of langchain.retrievers.weaviate_hybrid_search.WeaviateHybridSea…”
   • [github] “It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface…”

   proof ↗⚑ flag

   HelixDB—none0/10

   The evidence pack shows HelixDB has SDKs for Rust/TS/Go/Python and an MCP server, but there is no mention of any maintained LangChain, LlamaIndex, or other RAG/agent-framework integration. Community feedback even highlights the custom HelixQL query language as a barrier to easy AI-framework tooling, reinforcing the absence of first-class integrations.

   • [claimed-docs] “HelixDB v3 uses one operation-tree request model across the Rust, TypeScript, Go, and Python SDKs.”
   • [community] “At the moment I wouldn't consider HelixDB because of HelixQL. With OpenCypher even older cheap models can generate queries... by creating He…”
   • [community] “Can I run this as an embedded DB like sqlite? Can I sidestep the DSL? I want my LLMs to generate queries and using a new language is going t…”
   • [community] “This is very cool, and right up my alley. Hesitant to try it out because of the bespoke query language for now.”

   proof ↗⚑ flag

Sdks

1. developerBuild against official SDKs in the major languages (Python, TypeScript, Go, Java)

   weight 2 · round to Weaviate
   Weaviate✓fullclaimed8/10

   Official docs explicitly state client libraries are available in Python, JavaScript/TypeScript, Go, and Java, matching the story's exact language list. missing for 10: independent hands-on corroboration of each SDK's parity/quality, and no mention of versioning or release cadence across languages.

   • [claimed-docs] “Follow the instructions below to install one of the official client libraries, available in Python, JavaScript/TypeScript, Go, and Java.”

   proof ↗⚑ flag

   HelixDB~partialclaimed5/10

   Docs explicitly state a single operation-tree request model spanning Rust, TypeScript, Go, and Python SDKs, covering three of the four named languages plus Rust instead of Java. No evidence of a Java SDK exists in the pack. missing for 10: Java SDK, independent/hands-on corroboration of SDK quality across languages, deeper per-language SDK docs.

   • [claimed-docs] “HelixDB v3 uses one operation-tree request model across the Rust, TypeScript, Go, and Python SDKs.”

   proof ↗⚑ flag

Core search

1. developerRun approximate nearest-neighbor similarity search over embeddings with configurable distance metrics

   weight 3 · round to HelixDB
   Weaviate~partialprobed5/10

   Weaviate's core function as a vector database with semantic/vector similarity search is well evidenced (docs-22, docs-26, gh-4, probe-1 confirm it stores vectors and runs ANN-style similarity search, often combined with keyword search), but the evidence pack never explicitly documents configurable distance metrics (e.g., cosine, dot product, L2) or ANN indexing parameters like HNSW settings. Missing for 10: explicit documentation of selectable distance metrics, HNSW/ANN index configuration options, and independent hands-on confirmation of metric selection working as expected.

   • [claimed-docs] “By indexing data with vectors, Weaviate supports searches based on both semantic similarity and keywords.”
   • [claimed-docs] “Weaviate supports searches based on both semantic similarity and keywords. This allows for more relevant results even when the query terms d…”
   • [github] “It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.weaviate.io/llms.txt # Weaviate ## TL;DR Weaviate is an open-source vector database (Go) that sto…”
   • [github] “Weaviate supports two approaches to store vectors: automatic vectorization at import using integrated models ... or direct import of pre-com…”

   proof ↗⚑ flag

   HelixDB✓fullprobed8/10

   Docs explicitly describe vector indexes ranking node/edge embeddings by distance, requiring a non-zero dimension and a distance metric, plus approximate vector search confirmed in the llms.txt probe. This directly matches the ANN + configurable distance metric story, and it's combined with graph filtering for hybrid search. Missing for 10: no independent benchmark or hands-on confirmation of ANN recall/performance, and no enumeration of which specific distance metrics (cosine, L2, dot) are supported.

   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.helix-db.com/llms.txt # HelixDB > HelixDB combines a property graph, approximate vector search, an…”
   • [claimed-docs] “traverse and filter an exact candidate set before vector ranking, so results cannot escape graph or permission boundaries.”

   proof ↗⚑ flag

Hybrid

1. developerRun keyword/full-text search over documents inside the database without bolting on a separate search engine

   weight 2 · round drawn
   Weaviate✓fullclaimed8/10

   Weaviate natively supports BM25 keyword search combined with vector search via hybrid search (fusion algorithms), built directly into the database without needing a separate search engine like Elasticsearch. missing for 10: independent hands-on benchmarking of BM25-only relevance/performance, and clearer documentation on pure keyword-only query mode without vector component.

   • [claimed-docs] “Hybrid search combines vector search and keyword search (BM25) to leverage the strengths of both approaches.”
   • [claimed-docs] “Weaviate supports two strategies (`relativeScoreFusion` and `rankedFusion`) for combining vector and keyword search scores”
   • [claimed-docs] “A hybrid search runs both search types in parallel and combines their scores to produce a final ranking of results.”
   • [claimed-docs] “By indexing data with vectors, Weaviate supports searches based on both semantic similarity and keywords.”
   • [claimed-docs] “Weaviate supports searches based on both semantic similarity and keywords. This allows for more relevant results even when the query terms d…”
   • [github] “It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface…”

   proof ↗⚑ flag

   HelixDB✓fullprobed8/10

   Docs explicitly describe durable BM25 text indexes over string properties on nodes/edges as a native feature, confirmed by llms.txt describing BM25 full-text search as a first-class part of the engine alongside graph and vector search — no separate search engine needed. Missing for 10: independent hands-on benchmarks or community confirmation of full-text search quality/performance in practice.

   • [claimed-docs] “Text indexes provide durable BM25 search over string properties on nodes or edges.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.helix-db.com/llms.txt # HelixDB > HelixDB combines a property graph, approximate vector search, an…”
   • [claimed-docs] “Search and filtering on both nodes and edges, not just nodes.”

   proof ↗⚑ flag

2. developerCombine dense vector search with keyword or sparse (BM25-style) signals in one hybrid query with fusion ranking

   weight 3 · round to Weaviate
   Weaviate✓fullcommunity9/10

   Weaviate's docs explicitly describe hybrid search combining vector and BM25 keyword search with two fusion algorithms (relativeScoreFusion, rankedFusion) run in parallel and merged into a final ranking, matching the story precisely. Community discussion confirms real-world usage of hybrid search fusion (with minor confusion over fusion algorithm internals, not a failure). Missing for 10: no independent benchmark or hands-on quality comparison of fusion ranking accuracy.

   • [claimed-docs] “Hybrid search combines vector search and keyword search (BM25) to leverage the strengths of both approaches.”
   • [claimed-docs] “Weaviate supports two strategies (`relativeScoreFusion` and `rankedFusion`) for combining vector and keyword search scores”
   • [claimed-docs] “A hybrid search runs both search types in parallel and combines their scores to produce a final ranking of results.”
   • [github] “It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface…”
   • [community] “I feel like small formulas could clarify better these 2 fusion algorithms. I have read the article twice and checked some of the references …”

   proof ↗⚑ flag

   HelixDB~partialprobed5/10

   HelixDB documents separate vector indexes (distance-based ranking) and BM25 text indexes, and describes a unified operation-tree model that 'combines a property graph, approximate vector search, and BM25 full-text search' in one query engine, implying they can be used together. However, there is no explicit documentation of a fusion-ranking mechanism (e.g., weighted score combination or reciprocal rank fusion) that merges BM25 and vector scores into a single ranked result set within one query. Missing for 10: explicit fusion-ranking algorithm/API, a worked example combining BM25 and vector scores in one query, and independent confirmation of hybrid ranking quality.

   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”
   • [claimed-docs] “Text indexes provide durable BM25 search over string properties on nodes or edges.”
   • [claimed-docs] “traverse and filter an exact candidate set before vector ranking, so results cannot escape graph or permission boundaries.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.helix-db.com/llms.txt # HelixDB > HelixDB combines a property graph, approximate vector search, an…”

   proof ↗⚑ flag

Reranking

1. ml-engineerRerank search results with built-in or first-party-integrated reranking models

   weight 2 · round to Weaviate
   Weaviate~partialclaimed5/10

   Weaviate's GitHub README explicitly states it combines vector search, keyword filtering, RAG, and reranking in a single query interface, indicating built-in reranking support, but the evidence pack lacks first-party docs detailing specific reranker modules (e.g., Cohere, transformers) or configuration guidance. missing for 10: dedicated reranker-module docs, list of supported reranking providers, hands-on validation of reranking quality/behavior.

   • [github] “It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface…”

   proof ↗⚑ flag

   HelixDB—none0/10

   HelixDB documents vector, BM25 text, and hybrid graph-filtered vector search, but there is no evidence of built-in or first-party-integrated reranking models (e.g., cross-encoder rerankers) applied to search results; the pack only covers indexing and candidate retrieval, not a reranking stage.

   • [claimed-docs] “Vector indexes rank node or edge embeddings by distance. Every definition requires a non-zero dimension and a distance metric.”
   • [claimed-docs] “Text indexes provide durable BM25 search over string properties on nodes or edges.”
   • [claimed-docs] “traverse and filter an exact candidate set before vector ranking, so results cannot escape graph or permission boundaries.”

   proof ↗⚑ flag