feat: update serverless driver docs #7272
Conversation
Dangerous URL checkNo absolute URLs to prisma.io/docs found. |
WalkthroughAdds serverless-driver tip blocks to multiple Prisma Postgres getting-started pages, introduces a new comprehensive Prisma Postgres caching doc (Accelerate + invalidation), and updates database connection and pooling documentation to reflect Prisma ORM v7 driver-adapter defaults and expanded connection options. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes
Possibly related PRs
Pre-merge checks✅ Passed checks (3 passed)
Comment |
Redirect checkThis PR probably requires the following redirects to be added to static/_redirects:
|
Deploying docs with
|
| Latest commit: |
a1443e0
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://da64469d.docs-51g.pages.dev |
| Branch Preview URL: | https://dc-6266-serverless-driver.docs-51g.pages.dev |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
content/250-postgres/300-database/350-caching.mdx (1)
118-132: Paid plan requirement noted twice; consider consolidating.The note about on-demand cache invalidation requiring a paid plan appears in both the TTL invalidation section (line 129) and the SWR invalidation section (line 183). While the duplication reinforces an important constraint, consolidating this into a single prominent note (e.g., at the start of the "On-demand cache invalidation" section at line 259) would reduce repetition and improve readability.
Consider moving the paid plan note to the top of the "On-demand cache invalidation" section (before line 259) so users understand the constraint once, rather than learning it twice as they read through TTL and SWR examples.
Also applies to: 173-187
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (12)
content/100-getting-started/02-prisma-orm/100-quickstart/100-prisma-postgres.mdx(2 hunks)content/100-getting-started/02-prisma-orm/200-add-to-existing-project/100-prisma-postgres.mdx(2 hunks)content/100-getting-started/03-prisma-postgres/100-from-the-cli.mdx(2 hunks)content/100-getting-started/03-prisma-postgres/100-quickstart/50-prisma-orm.mdx(2 hunks)content/200-orm/050-overview/500-databases/200-database-drivers.mdx(4 hunks)content/200-orm/050-overview/500-databases/300-postgresql.mdx(2 hunks)content/200-orm/050-overview/500-databases/400-mysql.mdx(2 hunks)content/200-orm/050-overview/500-databases/800-sql-server/index.mdx(2 hunks)content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx(1 hunks)content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/index.mdx(1 hunks)content/250-postgres/300-database/350-caching.mdx(1 hunks)content/250-postgres/300-database/750-serverless-driver.mdx(1 hunks)
🧰 Additional context used
🧠 Learnings (5)
📚 Learning: 2025-10-08T16:23:00.388Z
Learnt from: aidankmcalister
Repo: prisma/docs PR: 7165
File: content/800-guides/550-test-guide.mdx:85-90
Timestamp: 2025-10-08T16:23:00.388Z
Learning: For .mdx files in the prisma/docs repository: All headings and titles should use sentence case (e.g., "Getting started with Prisma ORM", "Best practices for authentication"), not title case. Exception: Always preserve exact casing for product names including "Prisma Postgres", "Prisma", "Prisma ORM", and "Prisma Data Platform".
Applied to files:
content/200-orm/050-overview/500-databases/200-database-drivers.mdxcontent/100-getting-started/03-prisma-postgres/100-from-the-cli.mdxcontent/100-getting-started/02-prisma-orm/200-add-to-existing-project/100-prisma-postgres.mdxcontent/100-getting-started/03-prisma-postgres/100-quickstart/50-prisma-orm.mdxcontent/100-getting-started/02-prisma-orm/100-quickstart/100-prisma-postgres.mdx
📚 Learning: 2025-10-09T21:32:50.340Z
Learnt from: aidankmcalister
Repo: prisma/docs PR: 7167
File: content/900-ai/prompts/astro.mdx:84-84
Timestamp: 2025-10-09T21:32:50.340Z
Learning: The `npx prisma init` command supports the following flags: `--db` (shorthand for `--datasource-provider prisma+postgres`), `--output` (specifies output location for generated client), `--generator-provider` (defines the generator provider), `--datasource-provider`, `--url`, `--preview-feature`, and `--with-model`. These are documented valid CLI options for Prisma init command.
Applied to files:
content/200-orm/050-overview/500-databases/200-database-drivers.mdxcontent/100-getting-started/03-prisma-postgres/100-from-the-cli.mdxcontent/200-orm/050-overview/500-databases/400-mysql.mdxcontent/200-orm/050-overview/500-databases/300-postgresql.mdxcontent/100-getting-started/02-prisma-orm/200-add-to-existing-project/100-prisma-postgres.mdxcontent/100-getting-started/03-prisma-postgres/100-quickstart/50-prisma-orm.mdxcontent/100-getting-started/02-prisma-orm/100-quickstart/100-prisma-postgres.mdx
📚 Learning: 2025-08-11T09:40:55.237Z
Learnt from: ankur-arch
Repo: prisma/docs PR: 7066
File: content/200-orm/200-prisma-client/700-debugging-and-troubleshooting/245-troubleshooting-binary-size-issues.mdx:8-22
Timestamp: 2025-08-11T09:40:55.237Z
Learning: When the queryCompiler preview feature is enabled in Prisma ORM (v6.7.0+), it does not require Rust engines for CLI tools like `prisma migrate` or `prisma db pull`. The previous understanding that CLI tools would still need Rust binaries even with queryCompiler enabled is incorrect.
Applied to files:
content/100-getting-started/03-prisma-postgres/100-from-the-cli.mdxcontent/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/index.mdxcontent/100-getting-started/02-prisma-orm/200-add-to-existing-project/100-prisma-postgres.mdxcontent/100-getting-started/03-prisma-postgres/100-quickstart/50-prisma-orm.mdxcontent/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdxcontent/100-getting-started/02-prisma-orm/100-quickstart/100-prisma-postgres.mdx
📚 Learning: 2025-10-08T16:23:00.388Z
Learnt from: aidankmcalister
Repo: prisma/docs PR: 7165
File: content/800-guides/550-test-guide.mdx:85-90
Timestamp: 2025-10-08T16:23:00.388Z
Learning: For .mdx files in the prisma/docs repository: Only flag code snippets for (1) exposed secrets with real-looking values that should be placeholders (e.g., API keys, database passwords, AWS credentials), or (2) blatant syntax errors like missing parentheses, brackets, braces, or mismatched delimiters. Do not flag code quality issues, anti-patterns, security vulnerabilities, missing error handling, unused variables, or any other bad practices, as documentation intentionally shows problematic code.
Applied to files:
content/100-getting-started/03-prisma-postgres/100-from-the-cli.mdxcontent/100-getting-started/03-prisma-postgres/100-quickstart/50-prisma-orm.mdxcontent/100-getting-started/02-prisma-orm/100-quickstart/100-prisma-postgres.mdx
📚 Learning: 2025-10-08T16:22:57.129Z
Learnt from: aidankmcalister
Repo: prisma/docs PR: 7165
File: content/800-guides/550-test-guide.mdx:50-66
Timestamp: 2025-10-08T16:22:57.129Z
Learning: In `.mdx` files, do NOT flag or suggest changes for the following code quality issues even if they represent poor practices: React anti-patterns (using var instead of useState, direct DOM manipulation), missing keys in .map() iterations, non-serializable props in getServerSideProps, unused variables, missing error handling, SQL injection vulnerabilities (unless actively showing how to fix them), insecure cookie settings, missing TypeScript types, PrismaClient instantiation patterns, or any other code quality, security, or performance issues. Documentation code snippets are copied from source code and often intentionally show "before" examples or common mistakes.
Applied to files:
content/100-getting-started/03-prisma-postgres/100-from-the-cli.mdxcontent/100-getting-started/02-prisma-orm/200-add-to-existing-project/100-prisma-postgres.mdxcontent/100-getting-started/03-prisma-postgres/100-quickstart/50-prisma-orm.mdxcontent/100-getting-started/02-prisma-orm/100-quickstart/100-prisma-postgres.mdx
🪛 LanguageTool
content/100-getting-started/03-prisma-postgres/100-from-the-cli.mdx
[style] ~574-~574: Consider using an alternative to strengthen your wording.
Context: ...h a basic Prisma Postgres setup. If you want to explore more complex queries, such a...
(WANT_KEEN)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: Check internal links
- GitHub Check: Check links
- GitHub Check: Cloudflare Pages
🔇 Additional comments (30)
content/100-getting-started/02-prisma-orm/200-add-to-existing-project/100-prisma-postgres.mdx (2)
175-179: Serverless driver tip well-placed and consistent across guides.The tip block appropriately guides users to the serverless driver for edge-runtime HTTP queries, positioned right after the standard PrismaClient instantiation. The link anchor references the new "Use with Prisma ORM" section in the serverless driver docs.
265-265: Caching guidance link properly added to navigation.The "Cache your queries" link in the "More info" section references the new comprehensive caching setup section in the Prisma Postgres docs with the correct anchor.
content/200-orm/050-overview/500-databases/400-mysql.mdx (2)
117-117: Clarifies connection_limit scope for v6 and before.The update to the connection_limit table description properly scopes this parameter to Prisma ORM v6 and earlier, preparing users for the v7 driver-adapter paradigm shift where pooling is managed by the JavaScript driver.
133-135: v7 driver adapter tip well-integrated and educationally positioned.The tip block clearly explains that in v7, connection pooling is handled by the Node.js driver (mariadb) rather than Prisma URL parameters, with a helpful cross-reference to the connection pool guide. Positioned right after the URL arguments section, it surfaces the paradigm shift at the moment users are reading about legacy URL parameters.
content/100-getting-started/03-prisma-postgres/100-quickstart/50-prisma-orm.mdx (2)
186-190: Consistent serverless driver guidance across quickstart paths.The serverless driver tip is identical to the one in the add-to-existing-project guide, providing consistent messaging about edge-runtime HTTP query capabilities. Properly positioned after PrismaClient instantiation where developers are most likely to consider their deployment target.
260-260: Caching link maintains consistency across Prisma Postgres guides.The cache queries link placement and anchor reference align with other getting-started guides, providing unified navigation to the new caching documentation.
content/250-postgres/300-database/350-caching.mdx (2)
14-87: Comprehensive caching setup section with clear step-by-step guidance.The "Setting up caching in Prisma Postgres" section effectively onboards users with four clear steps: Platform Console enablement, extension installation, client configuration (with tabbed examples for standard/edge runtimes), and immediate query usage. The progression from setup to first cached query is logical and reduces friction.
212-258: Cache strategy guidance with practical use cases strengthens decision-making.The TTL+SWR combined strategy section provides both technical explanation and a real-world news article scenario, helping developers understand when and why to layer both parameters. The use case narratives (product catalogs, user profiles, news) ground the abstract caching concepts in concrete application patterns.
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx (2)
25-80: Strategic restructuring elevates v7 driver adapter guidance as primary path.Reorganizing the connection pool documentation to lead with "Relational databases" and immediately presenting v7 driver adapter defaults signals to users that this is the current recommended approach. The three driver-specific tables (PostgreSQL, MySQL/MariaDB, SQL Server) clearly map v6 URL parameters to v7 driver config fields, helping teams migrate their configuration understanding.
The tabular format (Behavior | v6 param | v6 default | v7 field | v7 default) makes side-by-side comparison intuitive, especially for
pool size,timeout, andconnection lifetimeconcepts that carry over conceptually but live in different places.
48-50: Driver-specific documentation references provide escape hatches for deep dives.The inline notes linking to node-postgres pool docs, MariaDB Connector docs, and node-mssql docs acknowledge that drivers have many tuning knobs beyond what's shown in the summary tables. Users who need to optimize further have clear next steps.
Also applies to: 63-65, 77-79
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/index.mdx (1)
268-285: v7 driver adapter education embedded at the right moment.When a developer is reading about pool size optimization, they learn that in v7, this optimization is now the responsibility of the JavaScript driver (pg, mariadb, mssql), not Prisma configuration. The generator config example shows the current default, and the note properly redirects them to the connection pool guide for v7-specific details. The blog link to performance benchmarks reinforces why this change was made.
content/250-postgres/300-database/750-serverless-driver.mdx (7)
1-10: metaDescription precisely communicates driver purpose and environment fit.The updated description—"A lightweight PostgreSQL driver for Prisma Postgres optimized for serverless and edge environments with HTTP/WebSocket support, result streaming, and minimal memory footprint"—immediately tells users and search engines what this driver is for. This clarity is essential for proper discovery.
18-30: Key features section provides immediate context for when to use this driver.By leading with HTTP/WebSocket transport, streaming, pipelining, and platform compatibility, users quickly understand the serverless driver's value proposition. The comparison to node-postgres (for Node.js environments) sets realistic expectations about when this driver is the right choice versus when the standard driver is better.
48-71: Installation tabs clearly separate dependency needs for different use cases.The split between "Without Prisma ORM" (just
@prisma/ppg) and "With Prisma ORM" (@prisma/ppg+@prisma/adapter-ppg) helps developers install exactly what they need. This reduces confusion and cognitive load.
73-163: Usage examples progress from simple to advanced, with clear API differentiation.The section structure—SQL template literals → Prisma ORM integration → streaming → pipelining → parameter streaming → transactions—mirrors a developer's journey from "how do I query?" to "how do I optimize for my use case?" The code examples are concrete and runnable.
186-250: Type handling section balances ease-of-use with extensibility.Showing that
defaultClientConfig()provides automatic parsing for common PostgreSQL types lowers the barrier to entry, while the custom parser and serializer examples demonstrate that the system is extensible. The use of PostgreSQL OID (2950 for UUID) and example code helps advanced users customize without guesswork.
252-265: Platform compatibility table at-a-glance confirms environment fit.The table clearly shows HTTP and WebSocket support across Cloudflare Workers, Vercel Edge Functions, AWS Lambda, Deno, Bun, Node.js, and browsers. Developers can instantly verify their deployment target is supported. The CORS note for browsers is a valuable caveat.
283-297: Error handling example demonstrates structured error types and proper handling pattern.The code snippet shows a real-world try/catch with
instanceof DatabaseErrorcheck, teaching developers idiomatic error handling for this driver. Mentioning additional error types (HttpResponseError, WebSocketError, ValidationError) signals the breadth of error scenarios without overwhelming.content/100-getting-started/02-prisma-orm/100-quickstart/100-prisma-postgres.mdx (2)
209-213: Serverless driver tip maintains consistent messaging across all Prisma Postgres quickstarts.The tip block is identical to those in the add-to-existing-project and quickstart-50-prisma-orm guides, ensuring users receive the same guidance regardless of which entry point they take into Prisma Postgres documentation. Properly positioned after the standard PrismaClient instantiation code.
283-283: Caching navigation link completes the Prisma Postgres getting-started loop.Adding the cache queries link to the "More info" section across all guides ensures users can naturally discover the new caching documentation after completing their initial setup. This unified navigation pattern reduces fragmentation and improves discoverability.
content/200-orm/050-overview/500-databases/800-sql-server/index.mdx (2)
123-123: Helpful clarification for the v6/v7 transition.The change clarifies that
connectionLimitis specific to Prisma ORM v6 and before, which guides users appropriately. This pairs well with the v7 tip added below and aligns with similar updates in PostgreSQL and MySQL documentation.
134-136: Clear v7 pooling guidance.The tip block concisely explains the architectural shift in Prisma ORM v7 (driver-managed pooling) and provides a direct link to the connection pool guide. This is consistent with similar blocks added to PostgreSQL and MySQL docs.
content/200-orm/050-overview/500-databases/200-database-drivers.mdx (3)
55-56: Prisma Postgres listed under both database and serverless adapters.Line 56 references
/postgres/database/serverless-driver#use-with-prisma-ormunder the "Database driver adapters" section, while Prisma Postgres is also listed separately under "Serverless driver adapters" at line 70. While this makes sense given Prisma Postgres's serverless-first design, readers may find it slightly confusing that a serverless driver appears in the database adapters section. This is probably fine as-is (since it still works with Node.js via the PPG adapter), but worth noting that the distinction is blurry.
55-56: Comprehensive and consistent Prisma Postgres integration.Prisma Postgres is added consistently across all three key locations (database adapters, serverless adapters, and usage guide), with identical links to the serverless driver documentation. This ensures discoverability and clear guidance on how to use Prisma Postgres with Prisma ORM.
Also applies to: 70-70, 85-85
153-157: Helpful tip for connection pool tuning.The tip block directs users to the connection pool guide for v7 defaults and configuration, which is a natural complement to the driver adapter setup instructions. This appears in two locations (also at lines 134-136 in the SQL Server file), which ensures visibility but also creates deliberate, helpful redundancy.
content/100-getting-started/03-prisma-postgres/100-from-the-cli.mdx (2)
297-301: Strategic serverless driver guidance.The tip is placed at an ideal moment—right after showing the standard TCP-based PrismaClient setup. This guides users toward the serverless driver when they need it (edge runtimes via HTTP), without making it mandatory for the basic getting-started flow. The specific use cases (Cloudflare Workers, Vercel Edge Functions) are helpful concrete examples.
574-574: More targeted next-steps link.Updating the next steps link from the generic quickstart to the specific caching guide (
/postgres/database/caching#setting-up-caching-in-prisma-postgres) is a better user journey—users who have completed the CLI setup are naturally ready to explore performance optimization features like caching. This aligns with the AI summary's note about expanding caching guidance.Please verify that the
/postgres/database/caching#setting-up-caching-in-prisma-postgresanchor exists in the Prisma Postgres caching documentation.content/200-orm/050-overview/500-databases/300-postgresql.mdx (3)
140-140: Consistent v6/v7 clarification across databases.The update to specify "(Prisma ORM v6 and before)" for
connection_limitmatches the same change in the SQL Server documentation, providing clear guidance for users on both versions.
163-165: Clear, consistent v7 pooling guidance.The tip block explains the shift to driver-managed pooling in Prisma ORM v7 and provides the connection pool guide reference. This wording is identical to the SQL Server version, which ensures consistency across the documentation. Placing this after the connection URL arguments is logical—it provides context for why some v6-specific parameters no longer apply.
144-155: I need to retrieve the actual parameter list from PostgreSQL documentation to complete the verification. Let me search for the detailed libpq parameters.I need to search more specifically for information about the parameters that don't appear in standard libpq documentation.
Clarify that this table documents Prisma PostgreSQL parameters, not native PostgreSQL libpq parameters.
Several parameters in this table are Prisma-specific extensions rather than native PostgreSQL libpq parameters. sslidentity is the path to a PKCS12 certificate database created from client cert and key, combining these files and securing them via a password. socket_timeout and pgbouncer (which disables prepared statement caching when enabled) are also Prisma-specific parameters not found in the PostgreSQL libpq documentation. The version annotations (2.1.0, 3.3.0, etc.) refer to Prisma versions, not PostgreSQL versions. While parameters like
sslcert,sslrootcert,application_name,channel_binding, andoptionsare valid libpq parameters, this table should be clearly labeled as documenting Prisma's PostgreSQL connection URL parameters to avoid reader confusion about what is native PostgreSQL versus Prisma-specific functionality.
🍈 Lychee Link Check Report
📊 Results Overview
Errors per inputErrors in 100-getting-started/02-prisma-orm/100-quickstart/400-mysql.mdx
Errors in 100-getting-started/02-prisma-orm/200-add-to-existing-project/400-mysql.mdx
Errors in 200-orm/050-overview/500-databases/400-mysql.mdx
Errors in 200-orm/100-prisma-schema/20-data-model/20-relations/410-referential-actions/index.mdx
Errors in 200-orm/100-prisma-schema/20-data-model/20-relations/420-relation-mode.mdxErrors in 200-orm/100-prisma-schema/20-data-model/30-indexes.mdx
Errors in 200-orm/200-prisma-client/100-queries/050-filtering-and-sorting.mdx
Errors in 200-orm/200-prisma-client/100-queries/058-transactions.mdx
Errors in 200-orm/200-prisma-client/100-queries/060-full-text-search.mdx
Errors in 200-orm/200-prisma-client/100-queries/070-case-sensitivity.mdx
Errors in 200-orm/200-prisma-client/150-using-raw-sql/200-raw-queries.mdx
Errors in 200-orm/300-prisma-migrate/050-getting-started.mdx
Errors in 200-orm/300-prisma-migrate/300-workflows/90-development-and-production.mdx
Errors in 200-orm/500-reference/100-prisma-schema-reference.mdx
Errors in 200-orm/500-reference/350-database-features.mdx
|
...-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx
Outdated
Show resolved
Hide resolved
…050-databases-connections/115-connection-pool.mdx
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx (2)
8-13: Clarify pool management behavior across Prisma versions in the opening context.Line 13 states that relational databases "use Prisma ORM's own connection pool," which is accurate for v6 and before but outdated for v7 context. Since the file now dedicates lines 25–79 to v7's driver-adapter model (where the underlying Node.js driver manages the pool), the opening should either:
- Lead with the v7 default and note the v6 legacy behavior separately, or
- Clarify that line 13 applies specifically to v6 and before.
This prevents readers from conflating Prisma-managed pools (v6) with driver-managed pools (v7).
Suggested revision for lines 8–13:
The query engine manages a **connection pool** of database connections. The pool is created when Prisma Client opens the _first_ connection to the database, which can happen in one of two ways: - By [explicitly calling `$connect()`](/orm/prisma-client/setup-and-configuration/databases-connections/connection-management#connect) _or_ - By running the first query, which calls `$connect()` under the hood -Relational database connectors use Prisma ORM's own connection pool, and the MongoDB connectors uses the [MongoDB driver connection pool](https://github.com/mongodb/specifications/blob/master/source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst). +Relational database connectors: + +- **Prisma ORM v7+**: Use the [driver adapter](/orm/overview/databases/database-drivers) model, where the underlying Node.js driver manages the connection pool. +- **Prisma ORM v6 and earlier**: Use Prisma ORM's own query-engine connection pool. + +MongoDB connectors use the [MongoDB driver connection pool](https://github.com/mongodb/specifications/blob/master/source/connection-monitoring-and-pooling/connection-monitoring-and-pooling.rst).
25-79: Excellent restructuring and mapping, but consider adding configuration guidance for v7.The tables (lines 32–79) provide a valuable v6→v7 parameter mapping with driver defaults. However, readers transitioning to v7 may not know how to apply these driver-adapter settings in practice. The v6 section (lines 95+) shows URL parameters in code, but v7 requires passing configuration to the driver adapter—a step not shown in the v7 section.
Consider adding a brief example showing how to configure these adapter settings in practice, or link to driver-adapter setup documentation that covers configuration.
For example, a snippet like:
### Configuring driver adapter pool settings With Prisma ORM v7 driver adapters, pass your pool configuration to the adapter constructor. For example, with the `pg` driver: \`\`\`ts import { PrismaPg } from '@prisma/adapter-pg' import { PrismaClient } from '@prisma/client' import pg from 'pg' const pool = new pg.Pool({ max: 15, // pool size idleTimeoutMillis: 5000, // ... other options }) const adapter = new PrismaPg(pool) const prisma = new PrismaClient({ adapter }) \`\`\`This closes the gap between understanding the pool defaults and implementing them.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx(1 hunks)
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2025-08-11T09:40:55.237Z
Learnt from: ankur-arch
Repo: prisma/docs PR: 7066
File: content/200-orm/200-prisma-client/700-debugging-and-troubleshooting/245-troubleshooting-binary-size-issues.mdx:8-22
Timestamp: 2025-08-11T09:40:55.237Z
Learning: When the queryCompiler preview feature is enabled in Prisma ORM (v6.7.0+), it does not require Rust engines for CLI tools like `prisma migrate` or `prisma db pull`. The previous understanding that CLI tools would still need Rust binaries even with queryCompiler enabled is incorrect.
Applied to files:
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
- GitHub Check: Check internal links
- GitHub Check: Cloudflare Pages
🔇 Additional comments (1)
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx (1)
48-50: Driver documentation references are well-placed and accurate.The tips point readers to authoritative driver-specific pool documentation (node-postgres, MariaDB Connector/Node.js, node-mssql), which is the right approach for configuration details that belong with the driver maintainers. This design choice avoids Prisma docs becoming outdated if driver defaults shift.
Also applies to: 63-65, 77-79
...nt/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/index.mdx
Show resolved
Hide resolved
…050-databases-connections/index.mdx
...-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx
Show resolved
Hide resolved
…050-databases-connections/115-connection-pool.mdx
There was a problem hiding this comment.
Actionable comments posted: 3
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx(1 hunks)
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2025-08-11T09:40:55.237Z
Learnt from: ankur-arch
Repo: prisma/docs PR: 7066
File: content/200-orm/200-prisma-client/700-debugging-and-troubleshooting/245-troubleshooting-binary-size-issues.mdx:8-22
Timestamp: 2025-08-11T09:40:55.237Z
Learning: When the queryCompiler preview feature is enabled in Prisma ORM (v6.7.0+), it does not require Rust engines for CLI tools like `prisma migrate` or `prisma db pull`. The previous understanding that CLI tools would still need Rust binaries even with queryCompiler enabled is incorrect.
Applied to files:
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: Check links
- GitHub Check: Check internal links
- GitHub Check: Cloudflare Pages
🔇 Additional comments (4)
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx (4)
36-40: Good clarification on Prisma vs. driver timeouts.The tip clearly separates Prisma Client timeouts from driver timeouts, which will help users debug timeout issues accurately. This addresses an important gap in the documentation.
87-89: No issues identified — architectural claim verified as accurate.The web search confirms the documentation statement is correct: the Prisma MongoDB connector does not use Prisma's built-in connection pool and delegates entirely to MongoDB's native driver pooling, which is configured via connection string parameters.
58-71: Documentation link is valid and current.The MariaDB Connector/Node.js pool options documentation link is available and accessible. The table accurately maps driver configuration fields and defaults between versions, and the reference to the official documentation is appropriate and current.
73-85: Configuration field names verified—consider clarifying millisecond units.The node-mssql pool configuration is accurate:
pool.max(default 10),connectionTimeout(default 15s), andpool.idleTimeoutMillis(default 30s) are the correct field names. The defaults match the API specification.However, the documentation presents these as seconds (15s, 30s), whereas the underlying API config accepts milliseconds. While the values are correct, adding a note that these are configured in milliseconds in the code would improve clarity for developers implementing the configuration.
| ## Relational databases | ||
|
|
||
| **When enabled, your Prisma Client will be generated without a Rust-based query engine binary**: | ||
| Starting with Prisma ORM v7, relational datasources instantiate Prisma Client with [driver adapters](/orm/overview/databases/database-drivers) by default. Driver adapters rely on the Node.js driver you supply, so connection pooling defaults (and configuration) now come from the driver itself. | ||
|
|
||
| ```prisma | ||
| generator client { | ||
| provider = "prisma-client" | ||
| output = "../src/generated/prisma" | ||
| engineType = "client" // no Rust engine | ||
| } | ||
| ``` | ||
| Use the tables below to translate Prisma ORM v6 connection URL parameters to the Prisma ORM v7 driver adapter fields alongside their defaults. |
There was a problem hiding this comment.
🧩 Analysis chain
Verify the v7 driver-adapter default claim.
Line 27 makes a significant architectural claim that "relational datasources instantiate Prisma Client with driver adapters by default" in v7. This is a major behavioral shift from v6, and users will rely on this being accurate for their migration planning.
🌐 Web query:
What is the default connection mechanism for relational databases in Prisma ORM v7? Are driver adapters the default for PostgreSQL, MySQL, and SQL Server?
💡 Result:
Short answer: Prisma v7 uses its built‑in drivers (the Query Engine) by default to connect to relational databases over TCP. Driver adapters (JavaScript/Node drivers like pg, mariadb, node‑mssql) are optional — available as preview/alternative — but are not the default for PostgreSQL, MySQL/MariaDB or SQL Server. [1][2][3]
Correct the v7 driver-adapter architectural claim — it is inaccurate.
The documentation states that driver adapters are "default" in v7, but this contradicts the actual architecture. Prisma v7 uses its built‑in drivers (the Query Engine) by default to connect to relational databases over TCP. Driver adapters are optional — available as preview/alternative — but are not the default.
Lines 25-29 need correction to reflect that the Query Engine remains the default connection mechanism, with driver adapters as an alternative option for users who need them (e.g., serverless environments, specific driver features).
| #### PostgreSQL (using the `pg` driver adapter) | ||
|
|
||
| ## Relational databases | ||
| Here are the default connection pool settings for the `pg` driver adapter: | ||
|
|
||
| | Behavior | v6 URL parameter | v6 default | v7 `pg` config field | v7 default | | ||
| | --- | --- | --- | --- | --- | | ||
| | Pool size | `connection_limit` | `num_cpus::get_physical() * 2 + 1` | `max` | `10` | | ||
| | Acquire timeout | `pool_timeout` | `10s` | `connectionTimeoutMillis` | `0` (no timeout) | | ||
| | Connection timeout | `connect_timeout` | `5s` | `connectionTimeoutMillis` | `0` (no timeout) | | ||
| | Idle timeout | `max_idle_connection_lifetime` | `300s` | `idleTimeoutMillis` | `10s` | | ||
| | Connection lifetime | `max_connection_lifetime` | `0` (no timeout) | `maxLifetimeSeconds` | `0` (no timeout) | | ||
|
|
||
| :::tip | ||
| See the [node-postgres pool documentation](https://node-postgres.com/apis/pool) for details on every available option. | ||
| ::: |
There was a problem hiding this comment.
🧩 Analysis chain
Clarify the pg driver timeout fields.
The table shows both "Acquire timeout" and "Connection timeout" mapping to connectionTimeoutMillis, but these should likely be different configuration fields in the pg driver. Line 49 shows connectionTimeoutMillis for acquire timeout, and line 50 also shows connectionTimeoutMillis for connection timeout. Please verify the actual pg driver API to confirm whether these map to the same field or if they should reference different fields (e.g., does the pg driver have separate acquire and connection timeout options?).
🌐 Web query:
What are the connection timeout and acquire timeout configuration options for the node-postgres (pg) driver? Are they the same field or different fields?
💡 Result:
Short answer: They are different. node-postgres (pg) exposes connectionTimeoutMillis on Pool (ms to wait when establishing a new client), but it does not provide an acquireTimeoutMillis option itself — "acquire timeout" is a separate concept used by other libraries (e.g. Knex or older generic-pool configs) to limit how long code waits for an idle client from the pool. See the pg Pool docs and the StackOverflow explanation. [1][2]
Sources:
- pg Pool options (connectionTimeoutMillis). [1]
- Explanation that pg-pool no longer uses the old generic-pool options (so acquireTimeoutMillis is not a built-in pg option). [2]
Fix the pg driver configuration table — acquire timeout is not a pg driver option.
The web search confirms that the pg driver only provides connectionTimeoutMillis for establishing new connections, and does not have an acquireTimeoutMillis option. Acquire timeout is a concept from other libraries (Knex, generic-pool), not the pg driver itself.
Lines 49–50 incorrectly show both "Acquire timeout" and "Connection timeout" mapping to connectionTimeoutMillis. The v7 pg config row for "Acquire timeout" (line 49) should be removed or clarified that the pg driver does not support this configuration option. Only connectionTimeoutMillis (for connection timeout) is applicable to the pg driver.
🤖 Prompt for AI Agents
In
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx
around lines 42–56, the table incorrectly lists an "Acquire timeout" mapped to
the pg driver and to connectionTimeoutMillis; the pg (node-postgres) driver does
not expose an acquire-timeout option. Remove the "Acquire timeout" row from the
pg driver table (or replace it with a single-cell note that pg does not support
an acquire timeout) and ensure the remaining "Connection timeout" row maps only
to connectionTimeoutMillis with the correct v7 default; update any explanatory
text to state that acquire-timeout is not available in pg and is a concept from
other pooling libraries.
| ## External connection poolers | ||
|
|
||
| You cannot increase the `connection_limit` beyond what the underlying database can support. This is a particular challenge in serverless environments, where each function manages an instance of `PrismaClient` - and its own connection pool. | ||
|
|
||
| Consider introducing [an external connection pooler like PgBouncer](/orm/prisma-client/setup-and-configuration/databases-connections#pgbouncer) to prevent your application or functions from exhausting the database connection limit. |
There was a problem hiding this comment.
🧩 Analysis chain
Verify external pooler guidance and PgBouncer documentation link.
The new external pooler section appropriately addresses serverless environments where connection pooling becomes critical. However, verify that:
- The internal link to PgBouncer documentation at
/orm/prisma-client/setup-and-configuration/databases-connections#pgbouncer(line 95) exists and is correctly formatted. - This section adequately signals that external poolers are required (not optional) for serverless/multi-instance deployments.
🏁 Script executed:
#!/bin/bash
# Verify that PgBouncer section exists in the connections documentation
find . -name "*databases-connections*" -type f | head -5Length of output: 0
I need to search the codebase more effectively. The initial find command didn't locate the file. Let me use a broader approach to find the connections documentation:
Once I locate the connections documentation file, I'll verify whether the PgBouncer section and its anchor exist.
---
🏁 Script executed:
```shell
#!/bin/bash
# Search for files in the content directory related to databases-connections
fd -t f "databases-connections" content/ 2>/dev/null | head -10
# Also search for any MDX files in the setup-and-configuration path
echo "---"
fd -t f "\.mdx$" "content/200-orm/200-prisma-client/000-setup-and-configuration/" 2>/dev/null | sort
Length of output: 1227
Now let me examine the PgBouncer file and the index structure to verify the link:
---
🏁 Script executed:
```shell
#!/bin/bash
# Check PgBouncer file for heading structure
echo "=== PgBouncer file content (first 50 lines) ==="
head -50 content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/200-pgbouncer.mdx
echo -e "\n=== Index file content ==="
cat content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/index.mdx
echo -e "\n=== Connection pool file lines 85-100 ==="
sed -n '85,100p' content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx
Length of output: 23992
Link verification complete; recommend strengthening language to signal pooler requirement.
The internal link to /orm/prisma-client/setup-and-configuration/databases-connections#pgbouncer is correctly formatted and resolves to the "### PgBouncer" section in the index file—no issues there.
However, the section's wording doesn't adequately signal that external poolers are required for serverless deployments. The current text uses "Consider introducing," which suggests an optional optimization rather than a critical necessity. For serverless/multi-instance contexts where exhausting database connections is a real risk, consider revising to language that more explicitly conveys the requirement—for example: "You should introduce an external connection pooler" or "External connection poolers are necessary to prevent..."
This aligns with the earlier guidance establishing the serverless challenge and would make the remediation pathway clearer to developers facing this constraint.
🤖 Prompt for AI Agents
In
content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx
around lines 91 to 95, the wording "Consider introducing an external connection
pooler" downplays the necessity of a pooler for serverless deployments; update
the text to clearly state that external connection poolers (e.g., PgBouncer) are
required in serverless/multi-instance contexts to avoid exhausting database
connections by replacing tentative language with a stronger directive such as
"You should introduce an external connection pooler" or "External connection
poolers are necessary to prevent your application or functions from exhausting
the database connection limit," and keep the link to the existing PgBouncer
anchor.
* feat: update serverless driver docs * feat: add connection pool defaults * feat: add query caching steps for prisma postgres * Update content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx * Update content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/index.mdx * Update content/200-orm/050-overview/500-databases/200-database-drivers.mdx * Update content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx
* DC-5044 `prisma-client-js` deprecated (#7219) * `prisma-client-js` deprecated * chore: empty commit * broken link updated * DC-5040 Env Vars via Config (#7227) * added env vars section to various pages * minor coderabbit updates * verbose removed * test removed redirect list * removed quickstart addition * converted quickstarts back * urls deprecated (#7226) * minimum version uodated (#7234) * DC-5043 Middleware removed from docs (#7233) * middleware deleted * more middleware removed * more middleware removed * coderabbit changes * DC-6174: Remove adapter, engine, directUrl, studio from config (#7256) * feat: add new features * fix: revert links * fix: broken links * fix: broken link * feat: restructure getting started side nav (#7245) * feat(docs): add youtube embeded link to blog post (#7220) Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> * feat(docs): add quick section to blog after the prompt (#7221) Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> * DC-5242 Astro Better-Auth Guide (#7215) * doc created * nextjs betterauth fixed * guide broken down into manageable steps * image added * Optimised images with calibre/image-actions * image updated * Optimised images with calibre/image-actions * lychee only comments on broken links * config updated * lychee updated based on CR comment * chore: trigger CI checks * ignore gnu * fix: update naming to better-auth DC-6120 * Optimised images with calibre/image-actions * chore: shorten word --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Ankur Datta <64993082+ankur-arch@users.noreply.github.com> * feat: restructure getting started side nav * DC-5841 Removed Linkspector (#7231) * removed linkspector * retrigger * retrigger * retrigger * Update label for Prisma Postgres tab (#7236) * fix: content changes for getting started page (#7216) * fix: content changes for getting started page * fix: add redirects * getting started checkpoint * css styles fixed * updates --------- Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> * DC-5820 AI Agents Served Markdown (#7237) * ai crawler check successful * ai crawlers checked * update * added anthropic * middleware update * improve detection --------- Co-authored-by: Mike Hartington <mikehartington@gmail.com> * feat: add prisma-orm quickstarts * fix: update times and add proper links * fix: instropspect changes * feat: add get started from prisma orm page * feat: add other orms * fix: update other tools + ppg * fix: add more clarity * fix: add prisma postgres * feat: clear migrate from early access * fix: add to existing dbs sections * Remove MCP server exploration tip (#7241) Removed tip about using Cloudflare's AI Playground for MCP server exploration, as it no longer seems to reliably work. * fix: clean-up docs files * fix: typeorm missing urls * fix: broken link * fix: update titles * fix: clear redirect loop (#7250) * fix: add generate step + sqlite fixes * fix: clean-up redirects file DC-6228 * fix: clean-up unnecessary file * fix: remove unknown word * fix: add links --------- Co-authored-by: Arthur <arthur_gamby@hotmail.fr> Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Petra Donka <donkapetra@gmail.com> Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Mike Hartington <mikehartington@gmail.com> * feat: update .env docs DC-6204 (#7259) * fix: clarify config file path better (#7261) * Update ORM docs (#7260) * update * use pg adapter instead of accelerate * update * add dotenv in prisma.config.ts * fix warning note * update * update * Update guides to use prisma.config.ts (#7243) * (feat) Update guides to use prisma.config.ts * refactor: Updated guides for Prisma 7 changes --------- Co-authored-by: Aman Varshney <amanvarshney.work@gmail.com> * feat: update ppg for other dbs section (#7264) * feat: add kysley * feat: add drizzle * feat: add typeorm * fix: clean-up * feat: separate the sections better * fix: remove badges * feat: update prisma init related changes in other parts (#7267) * feat: add kysley * feat: add drizzle * feat: add typeorm * fix: clean-up * fix: update prisma init command changes * feat: update prisma cli docs * fix: clarify the usage of prisma init better * fix: add type defs * feat: add pg as a dependency * fix: broken internal link * Update docs to perform migrations with connection pooling and Prisma config (#7266) * feat: add mentions of new Prisma Studio (#7270) * feat: add mentions of new Prisma Studio * feat: add note for Studio for SQLite * Update content/100-getting-started/02-prisma-orm/100-quickstart/200-sqlite.mdx * Update content/100-getting-started/02-prisma-orm/200-add-to-existing-project/200-sqlite.mdx * fix: make prisma studio docs more accurate * fix: add missing punctuation * feat: add mention of mongo support coming for P7 (#7271) * feat: add mention of mongo support coming for mongo * fix: refinements * Update content/100-getting-started/02-prisma-orm/200-add-to-existing-project/800-mongodb.mdx * (feat) Removes Accelerate specific instructions for Prisma Postgres (#7268) * (feat) Removes Accelerate specific instructions for Prisma Postgres * feat: update Deno integration guide to include additional development dependencies * Update Cloudflare D1 Guides (#7273) * feat: update serverless driver docs (#7272) * feat: update serverless driver docs * feat: add connection pool defaults * feat: add query caching steps for prisma postgres * Update content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx * Update content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/index.mdx * Update content/200-orm/050-overview/500-databases/200-database-drivers.mdx * Update content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx * docs(): add v7 migration guide (#7249) * docs(): add v7 migration guide * docs(): update based on feedback * Update content/200-orm/800-more/300-upgrade-guides/200-upgrading-versions/400-upgrading-to-prisma-7.mdx Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * docs(): update based on feedback * docs(): update based on feedback * docs(): update based on feedback --------- Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * update turso guide (#7274) * (feat) Explicitly running prisma generate after migrate dev command and import updates (#7276) * Update nuxt guides (#7275) * update nuxt guide * update * broken link fix * broken link fixed * fix: add SQLite notes (#7277) * fix: add SQLite notes * fix: update serverless driver doc * feat: add callout * Prisma 7 merge fix (#7278) * feat(docs): add youtube embeded link to blog post (#7220) Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> * feat(docs): add quick section to blog after the prompt (#7221) Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> * DC-5242 Astro Better-Auth Guide (#7215) * doc created * nextjs betterauth fixed * guide broken down into manageable steps * image added * Optimised images with calibre/image-actions * image updated * Optimised images with calibre/image-actions * lychee only comments on broken links * config updated * lychee updated based on CR comment * chore: trigger CI checks * ignore gnu * fix: update naming to better-auth DC-6120 * Optimised images with calibre/image-actions * chore: shorten word --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Ankur Datta <64993082+ankur-arch@users.noreply.github.com> * DC-5841 Removed Linkspector (#7231) * removed linkspector * retrigger * retrigger * retrigger * Update label for Prisma Postgres tab (#7236) * fix: content changes for getting started page (#7216) * fix: content changes for getting started page * fix: add redirects * getting started checkpoint * css styles fixed * updates --------- Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> * DC-5820 AI Agents Served Markdown (#7237) * ai crawler check successful * ai crawlers checked * update * added anthropic * middleware update * improve detection --------- Co-authored-by: Mike Hartington <mikehartington@gmail.com> * Remove MCP server exploration tip (#7241) Removed tip about using Cloudflare's AI Playground for MCP server exploration, as it no longer seems to reliably work. * fix: clear redirect loop (#7250) * Fix typo in environment variables reference (#7193) * Fix typo in environment variables reference * remove duplicate can be --------- Co-authored-by: Ankur Datta <64993082+ankur-arch@users.noreply.github.com> * chore(): add summary sections to top pages (#7228) * DC-6234 Getting Started Page Updates (#7254) * arrow added * quickstart card hover * always copy button added * hover effect on copy button * spcaer added * pointless css removed * updaets * fuctional * revewrt * fixed for mobile * link fix --------- Co-authored-by: Arthur <arthur_gamby@hotmail.fr> Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Ankur Datta <64993082+ankur-arch@users.noreply.github.com> Co-authored-by: Petra Donka <donkapetra@gmail.com> Co-authored-by: Mike Hartington <mikehartington@gmail.com> Co-authored-by: Odysseus Zhang <b1fzhang@gmail.com> Co-authored-by: Mike Hartington <mhartington@users.noreply.github.com> * spell check words added * Update content/100-getting-started/02-prisma-orm/100-quickstart/200-sqlite.mdx * `pgcrypto` added to spellcheck * Update content/100-getting-started/02-prisma-orm/100-quickstart/200-sqlite.mdx * Update content/100-getting-started/02-prisma-orm/100-quickstart/200-sqlite.mdx * Update content/100-getting-started/02-prisma-orm/100-quickstart/200-sqlite.mdx Co-authored-by: Ankur Datta <64993082+ankur-arch@users.noreply.github.com> * docs(): add note about vscode version pinning (#7279) * docs(): add note about vscode version pinning * Optimised images with calibre/image-actions * Update content/250-postgres/350-integrations/500-vscode.mdx Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * docs(postgres): remove accelerate reference (#7246) * DC-5044 `prisma-client-js` deprecated (#7219) * `prisma-client-js` deprecated * chore: empty commit * broken link updated * DC-5040 Env Vars via Config (#7227) * added env vars section to various pages * minor coderabbit updates * verbose removed * test removed redirect list * removed quickstart addition * converted quickstarts back * urls deprecated (#7226) * minimum version uodated (#7234) * DC-5043 Middleware removed from docs (#7233) * middleware deleted * more middleware removed * more middleware removed * coderabbit changes * DC-6174: Remove adapter, engine, directUrl, studio from config (#7256) * feat: add new features * fix: revert links * fix: broken links * fix: broken link * feat: restructure getting started side nav (#7245) * feat(docs): add youtube embeded link to blog post (#7220) Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> * feat(docs): add quick section to blog after the prompt (#7221) Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> * DC-5242 Astro Better-Auth Guide (#7215) * doc created * nextjs betterauth fixed * guide broken down into manageable steps * image added * Optimised images with calibre/image-actions * image updated * Optimised images with calibre/image-actions * lychee only comments on broken links * config updated * lychee updated based on CR comment * chore: trigger CI checks * ignore gnu * fix: update naming to better-auth DC-6120 * Optimised images with calibre/image-actions * chore: shorten word --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Ankur Datta <64993082+ankur-arch@users.noreply.github.com> * feat: restructure getting started side nav * DC-5841 Removed Linkspector (#7231) * removed linkspector * retrigger * retrigger * retrigger * Update label for Prisma Postgres tab (#7236) * fix: content changes for getting started page (#7216) * fix: content changes for getting started page * fix: add redirects * getting started checkpoint * css styles fixed * updates --------- Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> * DC-5820 AI Agents Served Markdown (#7237) * ai crawler check successful * ai crawlers checked * update * added anthropic * middleware update * improve detection --------- Co-authored-by: Mike Hartington <mikehartington@gmail.com> * feat: add prisma-orm quickstarts * fix: update times and add proper links * fix: instropspect changes * feat: add get started from prisma orm page * feat: add other orms * fix: update other tools + ppg * fix: add more clarity * fix: add prisma postgres * feat: clear migrate from early access * fix: add to existing dbs sections * Remove MCP server exploration tip (#7241) Removed tip about using Cloudflare's AI Playground for MCP server exploration, as it no longer seems to reliably work. * fix: clean-up docs files * fix: typeorm missing urls * fix: broken link * fix: update titles * fix: clear redirect loop (#7250) * fix: add generate step + sqlite fixes * fix: clean-up redirects file DC-6228 * fix: clean-up unnecessary file * fix: remove unknown word * fix: add links --------- Co-authored-by: Arthur <arthur_gamby@hotmail.fr> Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Petra Donka <donkapetra@gmail.com> Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Mike Hartington <mikehartington@gmail.com> * feat: update .env docs DC-6204 (#7259) * fix: clarify config file path better (#7261) * Update ORM docs (#7260) * update * use pg adapter instead of accelerate * update * add dotenv in prisma.config.ts * fix warning note * update * update * Update guides to use prisma.config.ts (#7243) * (feat) Update guides to use prisma.config.ts * refactor: Updated guides for Prisma 7 changes --------- Co-authored-by: Aman Varshney <amanvarshney.work@gmail.com> * feat: update ppg for other dbs section (#7264) * feat: add kysley * feat: add drizzle * feat: add typeorm * fix: clean-up * feat: separate the sections better * fix: remove badges * feat: update prisma init related changes in other parts (#7267) * feat: add kysley * feat: add drizzle * feat: add typeorm * fix: clean-up * fix: update prisma init command changes * feat: update prisma cli docs * fix: clarify the usage of prisma init better * fix: add type defs * feat: add pg as a dependency * fix: broken internal link * Update docs to perform migrations with connection pooling and Prisma config (#7266) * feat: add mentions of new Prisma Studio (#7270) * feat: add mentions of new Prisma Studio * feat: add note for Studio for SQLite * Update content/100-getting-started/02-prisma-orm/100-quickstart/200-sqlite.mdx * Update content/100-getting-started/02-prisma-orm/200-add-to-existing-project/200-sqlite.mdx * fix: make prisma studio docs more accurate * fix: add missing punctuation * feat: add mention of mongo support coming for P7 (#7271) * feat: add mention of mongo support coming for mongo * fix: refinements * Update content/100-getting-started/02-prisma-orm/200-add-to-existing-project/800-mongodb.mdx * docs(postgres): remove accelerate reference Remove reference to accelerate and rework the docs to account for the new v7 changes * Optimised images with calibre/image-actions * docs(): update with feedback * Optimised images with calibre/image-actions * docs(ppg): updates * docs(): update based on feedback * docs(): update based on feedback --------- Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> Co-authored-by: Ankur Datta <64993082+ankur-arch@users.noreply.github.com> Co-authored-by: Arthur <arthur_gamby@hotmail.fr> Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Petra Donka <donkapetra@gmail.com> Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Aman Varshney <amanvarshney.work@gmail.com> Co-authored-by: Nurul Sundarani <sundarani@prisma.io> * docs(metrics): remove metrics API (#7248) * DC-5044 `prisma-client-js` deprecated (#7219) * `prisma-client-js` deprecated * chore: empty commit * broken link updated * DC-5040 Env Vars via Config (#7227) * added env vars section to various pages * minor coderabbit updates * verbose removed * test removed redirect list * removed quickstart addition * converted quickstarts back * urls deprecated (#7226) * minimum version uodated (#7234) * DC-5043 Middleware removed from docs (#7233) * middleware deleted * more middleware removed * more middleware removed * coderabbit changes * docs(metrics): remove metrics API * DC-6174: Remove adapter, engine, directUrl, studio from config (#7256) * feat: add new features * fix: revert links * fix: broken links * fix: broken link * feat: restructure getting started side nav (#7245) * feat(docs): add youtube embeded link to blog post (#7220) Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> * feat(docs): add quick section to blog after the prompt (#7221) Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> * DC-5242 Astro Better-Auth Guide (#7215) * doc created * nextjs betterauth fixed * guide broken down into manageable steps * image added * Optimised images with calibre/image-actions * image updated * Optimised images with calibre/image-actions * lychee only comments on broken links * config updated * lychee updated based on CR comment * chore: trigger CI checks * ignore gnu * fix: update naming to better-auth DC-6120 * Optimised images with calibre/image-actions * chore: shorten word --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Ankur Datta <64993082+ankur-arch@users.noreply.github.com> * feat: restructure getting started side nav * DC-5841 Removed Linkspector (#7231) * removed linkspector * retrigger * retrigger * retrigger * Update label for Prisma Postgres tab (#7236) * fix: content changes for getting started page (#7216) * fix: content changes for getting started page * fix: add redirects * getting started checkpoint * css styles fixed * updates --------- Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> * DC-5820 AI Agents Served Markdown (#7237) * ai crawler check successful * ai crawlers checked * update * added anthropic * middleware update * improve detection --------- Co-authored-by: Mike Hartington <mikehartington@gmail.com> * feat: add prisma-orm quickstarts * fix: update times and add proper links * fix: instropspect changes * feat: add get started from prisma orm page * feat: add other orms * fix: update other tools + ppg * fix: add more clarity * fix: add prisma postgres * feat: clear migrate from early access * fix: add to existing dbs sections * Remove MCP server exploration tip (#7241) Removed tip about using Cloudflare's AI Playground for MCP server exploration, as it no longer seems to reliably work. * fix: clean-up docs files * fix: typeorm missing urls * fix: broken link * fix: update titles * fix: clear redirect loop (#7250) * fix: add generate step + sqlite fixes * fix: clean-up redirects file DC-6228 * fix: clean-up unnecessary file * fix: remove unknown word * fix: add links --------- Co-authored-by: Arthur <arthur_gamby@hotmail.fr> Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Petra Donka <donkapetra@gmail.com> Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Mike Hartington <mikehartington@gmail.com> * feat: update .env docs DC-6204 (#7259) * fix: clarify config file path better (#7261) * Update ORM docs (#7260) * update * use pg adapter instead of accelerate * update * add dotenv in prisma.config.ts * fix warning note * update * update * Update guides to use prisma.config.ts (#7243) * (feat) Update guides to use prisma.config.ts * refactor: Updated guides for Prisma 7 changes --------- Co-authored-by: Aman Varshney <amanvarshney.work@gmail.com> * feat: update ppg for other dbs section (#7264) * feat: add kysley * feat: add drizzle * feat: add typeorm * fix: clean-up * feat: separate the sections better * fix: remove badges * feat: update prisma init related changes in other parts (#7267) * feat: add kysley * feat: add drizzle * feat: add typeorm * fix: clean-up * fix: update prisma init command changes * feat: update prisma cli docs * fix: clarify the usage of prisma init better * fix: add type defs * feat: add pg as a dependency * fix: broken internal link * Update docs to perform migrations with connection pooling and Prisma config (#7266) * feat: add mentions of new Prisma Studio (#7270) * feat: add mentions of new Prisma Studio * feat: add note for Studio for SQLite * Update content/100-getting-started/02-prisma-orm/100-quickstart/200-sqlite.mdx * Update content/100-getting-started/02-prisma-orm/200-add-to-existing-project/200-sqlite.mdx * fix: make prisma studio docs more accurate * fix: add missing punctuation * feat: add mention of mongo support coming for P7 (#7271) * feat: add mention of mongo support coming for mongo * fix: refinements * Update content/100-getting-started/02-prisma-orm/200-add-to-existing-project/800-mongodb.mdx * Restore content/200-orm/200-prisma-client/600-observability-and-logging/240-metrics.mdx * docs(): update based on feedback * Update content/200-orm/200-prisma-client/000-setup-and-configuration/050-databases-connections/115-connection-pool.mdx Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> --------- Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> Co-authored-by: Ankur Datta <64993082+ankur-arch@users.noreply.github.com> Co-authored-by: Arthur <arthur_gamby@hotmail.fr> Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Petra Donka <donkapetra@gmail.com> Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Aman Varshney <amanvarshney.work@gmail.com> Co-authored-by: Nurul Sundarani <sundarani@prisma.io> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * fix build errors * fix * Add callout for bun and sqlite (#7280) * Add caalout for bun and sqlite * add link to bun docs * fix: get started path url (#7281) * fix: clarify studio better (#7282) * feat: add connection pooling gif (#7284) --------- Co-authored-by: Aidan McAlister <105178005+aidankmcalister@users.noreply.github.com> Co-authored-by: Arthur <arthur_gamby@hotmail.fr> Co-authored-by: Arthur Gamby <arthurgamby@Mac-002.lan> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Petra Donka <donkapetra@gmail.com> Co-authored-by: Aidan McAlister <aidankmcalister@gmail.com> Co-authored-by: Mike Hartington <mikehartington@gmail.com> Co-authored-by: Aman Varshney <amanvarshney.work@gmail.com> Co-authored-by: Nurul Sundarani <sundarani@prisma.io> Co-authored-by: Mike Hartington <mhartington@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Co-authored-by: Odysseus Zhang <b1fzhang@gmail.com>
Summary by CodeRabbit