DOC-790 | Importer & Retriever: Update startup parameters #809

nerpaula · 2025-10-17T11:51:00Z

Description

Importer & Retriever: Update startup parameters., including descriptions and parameters for instant and deep search.

Applying the changes to all versions no longer needed. The AI suite folder has been removed from the ArangoDB versioned folders.

arangodb-docs-automation · 2025-10-17T11:51:04Z

Deploy Preview Available Via
https://deploy-preview-809--docs-hugo.netlify.app

aMahanna

LGTM! minor comment about including embedding_api_provider

site/content/ai-suite/reference/importer.md

aMahanna · 2025-10-17T19:26:06Z

site/content/ai-suite/reference/importer.md

-        "openrouter_model": "mistralai/mistral-nemo"  // Specify a model here
+        "chat_api_provider": "openai",
+        "embedding_api_provider": "openai",
+        "chat_api_url": "https://openrouter.ai/api/v1",


This is fine - since setting openai as the provider means that we just use the OpenAI() client to interact with the OpenRouter URL, which is OpenAI-compatible

site/content/ai-suite/reference/importer.md

site/content/3.12/data-science/graphrag/services/retriever.md

diegomendez40

Added a couple of comments.

site/content/ai-suite/reference/importer.md

site/content/3.12/data-science/graphrag/services/retriever.md

bluepal-pavan-kothapalli · 2025-10-31T13:39:35Z

IMHO: It would be great if we could provide short documentation on how to create a project in genai-service.

Create a New Project

Endpoint: POST /v1/project

Validation: The name must be 1–63 characters long and can only contain letters, numbers, underscores, and hyphens.

Request Body:

json
{
"project_name": "my_project_1",
"project_type": "ML",
"project_description": "My project description"
}
This project can then be referenced in other services, like the importer or retriever, using the genai_project_name field:

json
{
"genai_project_name": "my_project_1"
}

WDYT?
CC @diegomendez40

nerpaula · 2025-10-31T13:45:18Z

IMHO: It would be great if we could provide short documentation on how to create a project in genai-service.

Create a New Project

Endpoint: POST /v1/project

Validation: The name must be 1–63 characters long and can only contain letters, numbers, underscores, and hyphens.

Request Body:

json { "project_name": "my_project_1", "project_type": "ML", "project_description": "My project description" } This project can then be referenced in other services, like the importer or retriever, using the genai_project_name field:

json { "genai_project_name": "my_project_1" }

WDYT? CC @diegomendez40

@bluepal-pavan-kothapalli There is a section on how to create a new project, in importer.md line 33. We should however reference this in the Retriever page as well.

cursor · 2025-10-31T14:53:30Z

You have run out of free Bugbot PR reviews for this billing cycle. This will reset on November 28.

To receive reviews on all of your PRs, visit the Cursor dashboard to activate Pro and start your 14-day free trial.

nerpaula · 2025-11-04T16:49:29Z

@diegomendez40 @bluepal-pavan-kothapalli FYI changes from my two latest commits:

remove username from startup parameters
add project_db_name as required parameter when creating a new project
after some careful consideration, I have decided that the Project endpoint deserves a better description and a section of its own in the GenAI Orchestrator service. I have further improved the content and moved it over. The Importer and Retriever have references to the respective section and marked as a prerequisite.

diegomendez40

Thanks for your work, @nerpaula. Unfortunately, I have found a number of possible enhancements and corrections.

While I added most of them to the 3.12 folder, they do also apply to 3.13.

site/content/ai-suite/reference/ai-orchestrator.md

diegomendez40 · 2025-11-04T18:00:02Z

site/content/ai-suite/reference/importer.md

- `triton_model`: Name of the LLM model to use for text processing.
-
-### Using OpenAI (Public LLM)
+### Using OpenAI for chat and embedding


"openai" doesn't stand for OpenAI, but rather for any OpenAI-compatible API, including essentially any large LLM provider: OpenRouter, Gemini, Anthropic, corporate LLMs, etc.

The URL can point to the relevant non-OpenAI endpoint, even if it is served via an OpenAI-compatible API.

diegomendez40 · 2025-11-04T18:00:54Z

site/content/ai-suite/reference/importer.md


 {{< info >}}
 By default, for OpenAI API, the service is using
 `gpt-4o-mini` and `text-embedding-3-small` models as LLM and
 embedding model respectively.
 {{< /info >}}

-### Using OpenRouter (Gemini, Anthropic, etc.)
+### Using OpenRouter for chat and OpenAI for embedding


It's not just OpenRouter. It's literally any OpenAI compatible API.

diegomendez40 · 2025-11-04T18:02:44Z

site/content/3.12/data-science/graphrag/services/retriever.md

+- **Instant search**: Focuses on specific entities and their relationships, ideal
+  for fast queries about particular concepts.
+- **Deep search**: Analyzes the knowledge graph structure to identify themes and patterns,
+  perfect for comprehensive insights and detailed summaries.


Unfortunately, these definitions are incorrect. These are the definitions for global and local. However, I had already provided the relevant definitions for instant vs. deep search, which can be used here.

diegomendez40 · 2025-11-04T18:03:44Z

site/content/3.12/data-science/graphrag/services/retriever.md

+Deep Search is designed for highly detailed, accurate responses that require understanding
+what kind of information is available in different parts of the knowledge graph and
+sequentially retrieving information in an LLM-guided research process. Use whenever
+detail and accuracy are required (e.g. aggregation of highly technical details) and
+very short latency is not (i.e. caching responses for frequently asked questions,
+or use case with agents or research use cases).


diegomendez40 · 2025-11-04T18:07:28Z

site/content/3.12/data-science/graphrag/services/retriever.md

 The request parameters are the following:
 - `query`: Your search query text.
- `level`: The community hierarchy level to use for the search (`1` for top-level communities).
+- `level`: The community hierarchy level to use for the search (`1` for top-level communities). Defaults to `2` if not provided.


You don't need the 'level' parameter. That's for global queries.

site/content/ai-suite/reference/retriever.md

diegomendez40 · 2025-11-04T18:10:34Z

site/content/3.12/data-science/graphrag/services/retriever.md

+  - `UNIFIED`: Instant search.
+  - `LOCAL`: Deep search.


This isn't exactly right.

Local with no LLM planner is the typical local query.

Local with LLM planner is Deep Search.

diegomendez40 · 2025-11-04T18:12:18Z

site/content/3.13/data-science/graphrag/services/importer.md

 {{< /info >}}

-### Using OpenRouter (Gemini, Anthropic, etc.)
+### Using OpenRouter for chat and OpenAI for embedding


Again, this should mention any OpenAI compatible API, not just OpenRouter

diegomendez40 · 2025-11-04T18:13:21Z

site/content/ai-suite/reference/retriever.md

+- **Instant search**: Focuses on specific entities and their relationships, ideal
+  for fast queries about particular concepts.
+- **Deep search**: Analyzes the knowledge graph structure to identify themes and patterns,
+  perfect for comprehensive insights and detailed summaries.


All changes above (on 3.12) should be replicated for 3.13.

Co-authored-by: Anthony Mahanna <43019056+aMahanna@users.noreply.github.com>

…tion rules

…oject creation; move and extend Projects

…eries

diegomendez40

Thanks for your work, @nerpaula.

This version is far better -- far more accurate. Still, I managed to find a couple of possible enhancements. Thanks for considering them before merging.

diegomendez40 · 2025-11-06T20:04:42Z

site/content/ai-suite/reference/gen-ai.md

+      "chat_api_provider": "<your-api-provider>",
+      "chat_api_key": "<your-llm-provider-api-key>",
+      "chat_model": "<model-name>"


I don't think this example is right.

You'd also need an embedding_api_provider:

https://github.com/arangoml/graphrag_importer/blob/main/charts/arangodb-graphrag-importer/templates/deployment.yaml#L1-L5

And then, due to the providers that we actually support, since you're already using a chat_api_key you're using an OpenAI-compatible API, which means you'd also need an embedding_api_key.

Just to be sure I'd use all these args:

- "db_name" - "chat_api_provider" - "embedding_api_provider" - "chat_model" - "embedding_model" - "chat_api_url" - "embedding_api_url" - "embedding_dim"

👀 @aMahanna @anyxling

Quick question about "embedding_dim". Should we add this to all examples, currently missing. Optional, I suppose? How can one decide the embedding dimension?

diegomendez40 · 2025-11-06T20:09:45Z

site/content/ai-suite/reference/retriever.md

-graph and get contextually relevant responses.
+The Retriever service provides intelligent search and retrieval from knowledge graphs,
+with multiple search methods optimized for different query types. The service supports 
+both private (Triton Inference Server) and public (any OpenAI-compatible API) LLM 


A corporate LLM isn't necessarily public. We've done projects with customers where we have been using their private LLMs via an OpenAI-compatible API.

Thus, the distinction private-Triton vs. public-OpenAI-compatible is false. OpenAI-compatible can be private.

diegomendez40 · 2025-11-06T20:18:18Z

site/content/ai-suite/reference/retriever.md


 The Retriever service can be configured to use either the Triton Inference Server
-(for private LLM deployments) or OpenAI/OpenRouter (for public LLM deployments).
+(for private LLM deployments) or any OpenAI-compatible API (for public LLM deployments), 


false private Triton/public OpenAI-compatible dichotomy

diegomendez40 · 2025-11-06T20:21:22Z

site/content/ai-suite/reference/retriever.md

-  - `1`: Global search.
-  - `2`: Local search.
+  - `GLOBAL` or `1`: Global Search (default if not specified).
+  - `LOCAL` or `2`: Deep Search when used with LLM planner, or standard Local Search without the planner.


Suggested change

- `LOCAL` or `2`: Deep Search when used with LLM planner, or standard Local Search without the planner.

- `LOCAL` or `2`: Deep Search when used with LLM planner (default), or standard Local Search when llm_planner is explicitly set to false.

diegomendez40 · 2025-11-06T20:21:48Z

site/content/ai-suite/reference/retriever.md

+  - `UNIFIED` or `3`: Instant Search.
+
+- `use_llm_planner`: Whether to use LLM planner for intelligent query orchestration (optional)
+  - When enabled, orchestrates retrieval using both local and global strategies (powers Deep Search)


Suggested change

- When enabled, orchestrates retrieval using both local and global strategies (powers Deep Search)

- When enabled (default), orchestrates retrieval using both local and global strategies (powers Deep Search)

bluepal-keerthi-datla · 2025-11-07T06:10:09Z

site/content/ai-suite/reference/importer.md

-By default, for OpenAI API, the service is using
-`gpt-4o-mini` and `text-embedding-3-small` models as LLM and
-embedding model respectively.
+When using the official OpenAI API, the service defaults to `gpt-4o-mini` and 


Docs say default models are gpt-4o-mini, but code uses gpt-4o. Please update docs to match actual behavior.

Refs: server.py:197, graph_builder.py:183

bluepal-keerthi-datla · 2025-11-07T06:13:05Z

site/content/ai-suite/reference/retriever.md

-By default, for OpenAI API, the service is using
-`gpt-4o-mini` and `text-embedding-3-small` models as LLM and
-embedding model respectively.
+When using the official OpenAI API, the service defaults to `gpt-4o-mini` and 


Same as mentioned above docs has the default model gpt-4o-mini, but the code uses gpt-4o. update the docs to reflect the actual behavior.

Refs: server.py:197, graph_builder.py:183

bluepal-keerthi-datla · 2025-11-07T06:22:03Z

site/content/ai-suite/reference/importer.md

-OpenRouter makes it possible to connect to a huge array of LLM API
-providers, including non-OpenAI LLMs like Gemini Flash, Anthropic Claude
-and publicly hosted open-source models.
+You can mix and match any OpenAI-compatible APIs for chat and embedding. For example, 


Docs currently state that chat and embedding providers can be mixed, but the code blocks this and raises an error:
server.py(149-154)
if args.chat_api_provider != args.embedding_api_provider:
raise ValueError("Chat API provider and embedding API provider must be the same.")

Please update the docs — either remove this section or mark it as a planned feature.
Suggested note:
Mixed provider support is planned. Currently, both chat_api_provider and embedding_api_provider must match (OpenAI or Triton).

@bluepal-keerthi-datla I wanted to illustrate in this example that you can use different OpenAI-compatible services - as in OpenRouter for chat and OpenAI for embeddings by setting both providers to "openai" and differentiating them with different URLs . I see that this can be confusing since both are considered the same provider type. I will change the section title to reflect this and clarify that you cannot mix Triton and OpenAI-compatible APIs.

@pid

* Experimental Platform split * WIP: Don't attempt to navigate to path but different version between Platform and Core docs * WIP: Navigation * Fix link * Test: Links between Platform and Core * Try to exclude aliases in link check * chore: update greens/reds * Hugo config: Temporarily disable aliases and exclude legacy versions * Preliminary support for versioned subfolders * Content re-organization and product renaming * Make core root folder not show cards for now * CircleCI: Increase time between config fetching attempts * WIP: New navigation scheme with inline version selector * chore: update logo, tweak colors * Theme: Add Urbanist font * Re-enable all core versions * Try Urbanist as font for headlines * CircleCI: Account for versions.yaml change when loading versions * Add optgroup to version selector with label "Version" * Set sans-serif as fallback font for headlines Less jarring change while the Urbanist font loads * Change tags due to renaming * Add EE tag tooltip for legacy content * Remove unnecessary tags * Move About ArangoDB out of versioned folder to ArangoDB top-level and move Features and Use cases under it * Add brand colors as CSS variables * Use Urbanist font for lead paragraph and card titles * Try electric lime as color for active nav items * Squashed commit of the following: commit e043896 Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 23 12:53:43 2025 +0200 Move image, add View node option commit 49fbafa Merge: d6f3359 cdd39d5 Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 23 10:13:04 2025 +0200 Merge branch 'main' of https://github.com/arangodb/docs-hugo into DOC-799 commit d6f3359 Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 23 10:12:58 2025 +0200 Review feedback, mention that nodes, edges, and theming is remembered commit cdd39d5 Author: Simran Spiller <simran@arangodb.com> Date: Wed Oct 22 15:29:13 2025 +0200 Toolchain: Set go version for arangoproxy to 1.24.0 The trailing .0 unbreaks builds for Vadim commit 976bf21 Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 15:25:16 2025 +0200 Vector index no longer experimental (#803) * Vector index no longer experimental * Rename startup option * Mention previous startup option name in release notes commit 311dee3 Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 15:15:34 2025 +0200 DOC-816 | Deduced vertex collections from named graphs (#799) * Release notes * Fix typo * Remove mention of vertexCollections and add section about graph queries in cluster for path searches * Modify release notes example * Fix/unify examples commit c2609c7 Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 15:07:29 2025 +0200 Vector indexes support filtering (#791) commit 4b7ab17 Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 15:02:22 2025 +0200 Unexpected Content-Length headers or invalid URLs report errors instead of closing connections (#795) commit 57056a0 Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 14:54:05 2025 +0200 DOC-805 | Extended memory accounting: COLLECT and MERGE() (#808) * Release notes for improved memory accounting: MERGE(), RETURN DISTINCT, and certain COLLECT operations * Mention already merged tracking features of internal buffers * Mention execution block tracking commit 7efadc3 Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 14:22:40 2025 +0200 Release notes for @pid@ and @TEMP_BASE_DIR@ startup option placeholders (#790) commit 3a78aec Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 14:21:53 2025 +0200 RocksDB upgrade to 9.5.0 release notes (#710) * WIP: RocksDB upgrade to 9.5.0 release notes * Throttling wasn't changed * Apply to 3.13 * Clarify units * Some RocksDB startup option defaults have been reverted * Fix merge error * Fix merge mistake --------- Co-authored-by: Paula Mihu <97217318+nerpaula@users.noreply.github.com> commit d596f51 Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 14:13:31 2025 +0200 Sparse vector indexes (#770) * Vector index type now supports sparse option * Use same wording for sparse HTTP API docs, replace hash with persistent index, fix statements about estimates --------- Co-authored-by: Paula Mihu <97217318+nerpaula@users.noreply.github.com> commit 3de2dbf Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 14:10:36 2025 +0200 Release notes about deprecation of --rocksdb.transaction-lock-timeout startup option (#762) Co-authored-by: Paula Mihu <97217318+nerpaula@users.noreply.github.com> commit 73428ea Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 14:09:39 2025 +0200 DOC-776 | AQL query recording (#735) * AQL query recording API * Fix text about startup option, add more status codes * Rework release notes, adjust attribute names * Fix copy-paste mistake * Per Coordinator recording in clusters * fix merge error --------- Co-authored-by: Paula Mihu <97217318+nerpaula@users.noreply.github.com> Co-authored-by: Paula <paula.mihu@arangodb.com> commit 85de2a3 Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 14:08:47 2025 +0200 DOC-772 | `GEO_POINT()` accepts elevation but z coordinate is ignored in geo functions / validation of points in `GEO_MULTIPOINT()` and `GEO_(MULTI_)LINESTRING` (#733) * GEO_POINT() accepts elevation but z coordinate is ignored in geo functions * Add more details * Add introduced in 3.11 * Add release notes about point validation in AQL GeoJSON functions * Fix order --------- Co-authored-by: Paula Mihu <97217318+nerpaula@users.noreply.github.com> commit 9cc6d81 Author: Simran <Simran-B@users.noreply.github.com> Date: Wed Oct 22 14:05:25 2025 +0200 DOC-765 | Cosine similarity fix for vector indexes (#719) * Initial reference docs about the vector index * HTTP API docs and refinements * Version remark, OpenAPI minItems/maxItems and fix a type * inBackground and parallelism are supported * Review feedback, address cosine metric issue, reword inBackground, add parallelism * Remove leftover line * Add internal links to release notes * Cosine similarity value out of range has been fixed * Add innerProduct metric --------- Co-authored-by: Paula Mihu <97217318+nerpaula@users.noreply.github.com> commit 4f7090e Author: Simran Spiller <simran@arangodb.com> Date: Wed Oct 22 14:04:12 2025 +0200 Toolchain: Set lower 1.24 Go version as minimum for arangoproxy Go 1.25 is only available in alpine:edge at the moment commit 6594ebc Author: Simran Spiller <simran@arangodb.com> Date: Wed Oct 22 13:25:11 2025 +0200 Fix path for icon shortcode commit c12be47 Author: Simran Spiller <simran@arangodb.com> Date: Wed Oct 22 13:17:25 2025 +0200 Review feedback commit 14003ce Author: Simran Spiller <simran@arangodb.com> Date: Wed Oct 22 13:14:53 2025 +0200 Change icon shortcode image path commit 1fc696f Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 21 23:23:28 2025 +0200 Icons: Move settings icon to the canvas center commit 9b3b338 Author: Michele Rastelli <michele@arangodb.com> Date: Tue Oct 14 16:49:33 2025 +0200 updated ArangoDB Tinkerpop Provider limitations (#806) commit cc2db4d Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 16:13:52 2025 +0200 Fix edge styling options commit 4492cf6 Author: Michele Rastelli <michele@arangodb.com> Date: Tue Oct 14 15:53:54 2025 +0200 [DE-1040] ArangoDB Tinkerpop Provider: initial documentation (#750) * ArangoDB Tinkerpop Provider: initial documentation * fixed links * review * updated GraphFeatures * doc: gremlin console (DE-1062) * doc: gremlin server (DE-1061) * updated tinkerpop version to 3.7.4 * doc: fix complex id format * removed collection name prefix restriction * configurable label field name (DE-1070) * query optimizations * review; add content to all versions * keep vertex instead of node to align with tinkerpop concepts and terminology --------- Co-authored-by: Paula Mihu <97217318+nerpaula@users.noreply.github.com> Co-authored-by: Paula <paula.mihu@arangodb.com> commit c38b58e Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 15:49:27 2025 +0200 Minor fixes commit f1600ef Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 15:36:28 2025 +0200 Update visual customization part commit 144f44d Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 15:36:02 2025 +0200 Extend README for icon shortcode commit 22d82c8 Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 11:37:39 2025 +0200 Rename icon files and mention icon shortcode to README commit 62860ef Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 11:00:24 2025 +0200 DOC-813 | Implement icon shortcode and add Graph Visualizer icons commit 0f718a1 Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 10:59:15 2025 +0200 Update descriptions commit 5ee3e0d Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 10:22:55 2025 +0200 Update customization screenshot commit 4d61a71 Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 9 12:39:09 2025 +0200 Icon shortcode prototype commit c595f25 Merge: 155a71a 8a3c37d Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 9 10:27:01 2025 +0200 Merge branch 'main' of https://github.com/arangodb/docs-hugo into DOC-799 commit 155a71a Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 9 10:26:51 2025 +0200 Update Visualizer screenshots commit 8a3c37d Author: Paula Mihu <97217318+nerpaula@users.noreply.github.com> Date: Tue Oct 7 16:06:14 2025 +0200 OAS-11485 | Add warning regarding single server upgrade to cluster in ArangoGraph (#798) * add warning regarding single server upgrade to cluster * apply to 3.11 as well commit a570281 Author: Paula Mihu <97217318+nerpaula@users.noreply.github.com> Date: Tue Oct 7 16:03:49 2025 +0200 move gae content into genai chapter (#796) commit 1f925ce Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 2 09:55:57 2025 +0200 WIP * Unrelated consistency changes * Squashed commit of the following: commit f005cb3 Author: Paula <paula.mihu@arangodb.com> Date: Thu Oct 23 13:22:52 2025 +0200 fix broken links commit cb0629b Author: Paula <paula.mihu@arangodb.com> Date: Thu Oct 23 13:13:55 2025 +0200 remove tag for now commit 2474431 Author: Paula <paula.mihu@arangodb.com> Date: Wed Oct 22 19:29:42 2025 +0200 Renamed GenAI Suite to AI Services across all files, including endpoints; renamed Services folder to Reference; fix all broken links commit 80fb229 Author: Paula <paula.mihu@arangodb.com> Date: Thu Oct 16 10:27:08 2025 +0200 fix some broken links commit 52b1f2a Author: Paula <paula.mihu@arangodb.com> Date: Wed Oct 15 18:11:59 2025 +0200 reorganize genai suite overview pages commit f54dce1 Author: Paula <paula.mihu@arangodb.com> Date: Thu Oct 9 16:55:42 2025 +0200 added graphrag uses cases, reorganize content commit 50ea476 Author: Paula <paula.mihu@arangodb.com> Date: Wed Oct 15 17:10:38 2025 +0200 rework data platform content, make kubernetes more prominent commit 4249c4e Author: Paula <paula.mihu@arangodb.com> Date: Tue Oct 14 16:55:41 2025 +0200 rename ArangoDB Platform to Arango Data Platform commit abc5079 Author: Paula <paula.mihu@arangodb.com> Date: Tue Oct 14 16:50:32 2025 +0200 change menu titles * Update tag tooltips * Fix tab name in Graph Analytics * Graph Intelligence -> Graphs also in menu * ArangoGraph -> AMP in oasisctl generator * Change cloud banner alt text * Rename AI Services back to AI Suite Also fix oasisctl page and name capitalization * Squashed commit of the following: commit f15a592 Merge: e043896 4480ca8 Author: Simran <Simran-B@users.noreply.github.com> Date: Sat Oct 25 23:30:53 2025 +0200 Merge branch 'main' into DOC-799 commit e043896 Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 23 12:53:43 2025 +0200 Move image, add View node option commit 49fbafa Merge: d6f3359 cdd39d5 Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 23 10:13:04 2025 +0200 Merge branch 'main' of https://github.com/arangodb/docs-hugo into DOC-799 commit d6f3359 Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 23 10:12:58 2025 +0200 Review feedback, mention that nodes, edges, and theming is remembered commit 6594ebc Author: Simran Spiller <simran@arangodb.com> Date: Wed Oct 22 13:25:11 2025 +0200 Fix path for icon shortcode commit c12be47 Author: Simran Spiller <simran@arangodb.com> Date: Wed Oct 22 13:17:25 2025 +0200 Review feedback commit 14003ce Author: Simran Spiller <simran@arangodb.com> Date: Wed Oct 22 13:14:53 2025 +0200 Change icon shortcode image path commit 1fc696f Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 21 23:23:28 2025 +0200 Icons: Move settings icon to the canvas center commit cc2db4d Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 16:13:52 2025 +0200 Fix edge styling options commit c38b58e Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 15:49:27 2025 +0200 Minor fixes commit f1600ef Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 15:36:28 2025 +0200 Update visual customization part commit 144f44d Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 15:36:02 2025 +0200 Extend README for icon shortcode commit 22d82c8 Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 11:37:39 2025 +0200 Rename icon files and mention icon shortcode to README commit 62860ef Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 11:00:24 2025 +0200 DOC-813 | Implement icon shortcode and add Graph Visualizer icons commit 0f718a1 Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 10:59:15 2025 +0200 Update descriptions commit 5ee3e0d Author: Simran Spiller <simran@arangodb.com> Date: Tue Oct 14 10:22:55 2025 +0200 Update customization screenshot commit 4d61a71 Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 9 12:39:09 2025 +0200 Icon shortcode prototype commit c595f25 Merge: 155a71a 8a3c37d Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 9 10:27:01 2025 +0200 Merge branch 'main' of https://github.com/arangodb/docs-hugo into DOC-799 commit 155a71a Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 9 10:26:51 2025 +0200 Update Visualizer screenshots commit 1f925ce Author: Simran Spiller <simran@arangodb.com> Date: Thu Oct 2 09:55:57 2025 +0200 WIP * New domain, Arango team/support * Whitespace control and typo * Simplify logic for in-development warning with a flag in versions.yaml * Fix and refactor breadcrumbs Make long version numbers for core work and switch from Microdata to RDFa * Set metadata for search engines noindex for deprecated and in-development versions, canonical link from stable version (e.g. 3.12) to stable alias * Toolchain: Adjust oasisctl generator for new docs structure and improve output * Move drivers & integrations under Ecosystem (#816) * rename data science adapters * Move 3.12 drivers and integrations under ecosystem, fix links * remove drivers and integrations from 3.13, add aliases * fix broken link due to double slash * fix more broken links * Revert links to drivers and integrations in 3.10 and 3.11 * Fix link * Fix driver headline * EOL support for Spark 3.3 --------- Co-authored-by: Simran Spiller <simran@arangodb.com> * Attribute-based theming (#821) * Docs homepage content (#819) * WIP: Docs homepage content Reuses the Graph to AI page * add avocado icons to product cards, remove old images * Adjust card CSS to float an icon to the right of the title * Rework homepage and ArangoDB introduction - New and reworked sections for From Graph to AI for a full journey - Move knowledge graph definition to GraphRAG - Remove outdated ArangoDB diagram from overview and mention self-managed cloud deployments - Use card shortcode icon parameter --------- Co-authored-by: Paula <paula.mihu@arangodb.com> Co-authored-by: Paula Mihu <97217318+nerpaula@users.noreply.github.com> * Update Inkeep config * Toolchain: generate-oasisctl workflow no longer needs arangodb-X_XX (upstream references) * DOC-812 | New Query Editor & AQLizer feature page (#810) * Initial content about the new Query Editor * Describe how to work with/generate queries and adjust the viewport * Remembered/saved queries, product naming * Capitalize Query Editor, long page title * Add icons, update product name * Query management, AQLizer setup and feature overview * Remove Experimental tag * Add AQLizer to list of major AI Suite components * Add screenshot * AQLizer screenshot, hotkey, and Open in Editor button * Crop screenshot * Data Platform | Add dedicated K8s page and detailed descriptions (architecture/components) (#814) * data platform for amp is available upon request * Add new Kubernetes page; Add detailed descriptions of Data Platform's architecture and components * Apply suggestions from code review Co-authored-by: Simran <Simran-B@users.noreply.github.com> * apply review suggestions * Apply suggestion from @nerpaula * review * Fix link --------- Co-authored-by: Simran <Simran-B@users.noreply.github.com> Co-authored-by: Simran Spiller <simran@arangodb.com> * DOC-797 | Natural language to AQL service (txt2aql / AQLizer) (#794) * initial draft * add process-text-stream * add info box and placeholder for external endpoint URL * clarify provider-specific parameters, add OpenRouter, genai project no longer needed, add aqlizer mode * remove grpc (only internal use) * remove triton * apply review suggestions * apply suggestion Co-authored-by: maxkernbach <maximilian.kernbach@gmail.com> * Fix link * add missing https prefix in curl example URL --------- Co-authored-by: maxkernbach <maximilian.kernbach@gmail.com> Co-authored-by: Simran Spiller <simran@arangodb.com> * DOC-800 | New GraphRAG UI steps (#805) * new graphrag ui * finalize content, remove unnecessary screenshots, apply to all versions * update screenshot, fix typo * Fix image reference --------- Co-authored-by: Simran Spiller <simran@arangodb.com> * WIP: New navigation * Fix versioned submenu visibility * Fix active state for hard navigation and better expand widget * Replace versions in arangodb links on the client-side Hugo does not regenerate the content if it's mounted twice, so the links in /stable and /devel use /3.12 and /3.13 * Adjust cards on root page of 3.12 and 3.13 These pages are not accessble from the nav but via the breadcrumbs for instance. Should not be linked to. * Fix go to homepage * Rework mobile menu toggle Fix functionality, use event listener, remove unused CSS, fix references in JS * Fix version and error handling * Hide mobile navigation on click * Data Platform & AI Suite | October release notes (#824) * add release notes * Review --------- Co-authored-by: Simran Spiller <simran@arangodb.com> * DOC-815 | MCP Server (#820) * add initial content for MCP server * remove installation content and just link to docker hub * Leave the navigation closed by default on mobile * Restructuring and version for Data Platform (#823) * Data Platform is version 3 * Rename AQL > Graphs to AQL > Graph queries * Change Data Platform version to "v3.0" * Rename index-and-search -> indexes-and-search * Move arango-datasets to Ecosystem * Different admonitions for Data Platform and AI Suite * Rename 3.13 to 4.0 * Rename gen-ai.md service to ai-orchestrator.md * Don't link to version root page, don't change page when on ArangoDB root * Change menu title AMP API -> API * Update Graph Visualizer screenshot * DOC-790 | Importer & Retriever: Update startup parameters (#809) * update startup parameters * Apply suggestions from code review Co-authored-by: Anthony Mahanna <43019056+aMahanna@users.noreply.github.com> * apply changes to all versions, fix typo * instant and deep search * update description of instant and deep search; fix some anchor links * add missing description for chat_api_url * fix typo * reference project creation in retriever file; add project name validation rules * remove username from startup parameters * update startup parameters in genai service; add project_db_name in project creation; move and extend Projects * clarify project requirements; clarify OpenAI-compatible API usage * restructure and clarify all available search methods and executing queries * address review comments * update links --------- Co-authored-by: Anthony Mahanna <43019056+aMahanna@users.noreply.github.com> * Update tracking * Cleanup * Remove home.html to use regular list.html This adds the footer with the next link so that there is space at the bottom to avoid the content overlapping the Back to Top and Ask AI buttons * Tweak styling of nav scrollbar and version selector * Remove test links * Remove old aliases * Contribute link: Substitute version alias with version name to point to actual file on GitHub * Remove code that replaced the version in the URL with the selected one Also disable some logging * Align 3.10 and 3.11 structure with later versions (features, use cases, graph queries, indexes & search) and add aliases to avoid certain 404 pages when using the version switcher * DOC-811 | Update ArangoGraph screenshots to AMP (#828) * update arangograph screenshots (wip) * replace more images, remove unnecessary ones * remove all remaining arangograph images * remove arangograph ml image * remove arangographml image from ai-suite * Optimize PNGs with Bulk Squoosh --------- Co-authored-by: Simran Spiller <simran@arangodb.com> * Replace and remove links to arangodb.com --------- Co-authored-by: Palash Karia <2976363+palashkaria@users.noreply.github.com> Co-authored-by: Paula Mihu <97217318+nerpaula@users.noreply.github.com> Co-authored-by: Paula <paula.mihu@arangodb.com> Co-authored-by: maxkernbach <maximilian.kernbach@gmail.com> Co-authored-by: Anthony Mahanna <43019056+aMahanna@users.noreply.github.com>

cla-bot bot added the cla-signed label Oct 17, 2025

nerpaula self-assigned this Oct 17, 2025

This comment was marked as outdated.

Sign in to view

aMahanna reviewed Oct 17, 2025

View reviewed changes

nerpaula commented Oct 24, 2025

View reviewed changes

site/content/3.12/data-science/graphrag/services/retriever.md Outdated Show resolved Hide resolved

nerpaula commented Oct 24, 2025

View reviewed changes

site/content/3.12/data-science/graphrag/services/retriever.md Outdated Show resolved Hide resolved

diegomendez40 reviewed Oct 24, 2025

View reviewed changes

diegomendez40 requested a review from bluepal-pavan-kothapalli October 31, 2025 12:08

bluepal-pavan-kothapalli reviewed Oct 31, 2025

View reviewed changes

site/content/ai-suite/reference/importer.md Show resolved Hide resolved

bluepal-pavan-kothapalli reviewed Oct 31, 2025

View reviewed changes

site/content/ai-suite/reference/importer.md Outdated Show resolved Hide resolved

bluepal-pavan-kothapalli reviewed Oct 31, 2025

View reviewed changes

site/content/3.12/data-science/graphrag/services/retriever.md Outdated Show resolved Hide resolved

diegomendez40 requested changes Nov 4, 2025

View reviewed changes

nerpaula and others added 10 commits November 4, 2025 22:05

update startup parameters

a4dd3b5

Apply suggestions from code review

a32d841

Co-authored-by: Anthony Mahanna <43019056+aMahanna@users.noreply.github.com>

apply changes to all versions, fix typo

02adb50

instant and deep search

3504267

update description of instant and deep search; fix some anchor links

bec2f30

add missing description for chat_api_url

b33024b

fix typo

e48a6d0

reference project creation in retriever file; add project name valida…

81d49fb

…tion rules

remove username from startup parameters

e657d19

update startup parameters in genai service; add project_db_name in pr…

52176ce

…oject creation; move and extend Projects

Simran-B force-pushed the DOC-790 branch from cbb782f to 52176ce Compare November 4, 2025 21:26

Simran-B changed the base branch from main to DOC-761 November 4, 2025 21:27

Merge branch 'DOC-761' into DOC-790

b764373

nerpaula added 2 commits November 5, 2025 20:50

clarify project requirements; clarify OpenAI-compatible API usage

dcc8be1

restructure and clarify all available search methods and executing qu…

59cdb87

…eries

nerpaula requested a review from diegomendez40 November 6, 2025 12:08

diegomendez40 requested review from bluepal-keerthi-datla and bluepal-pavan-kothapalli November 6, 2025 15:02

diegomendez40 approved these changes Nov 6, 2025

View reviewed changes

bluepal-keerthi-datla reviewed Nov 7, 2025

View reviewed changes

nerpaula added 3 commits November 7, 2025 11:28

address review comments

037006d

Merge DOC-761 into DOC-790

27deb24

update links

a9dfd67

nerpaula merged commit 6652b51 into DOC-761 Nov 10, 2025
5 checks passed

nerpaula deleted the DOC-790 branch November 10, 2025 12:42

	- `LOCAL` or `2`: Deep Search when used with LLM planner, or standard Local Search without the planner.
	- `LOCAL` or `2`: Deep Search when used with LLM planner (default), or standard Local Search when llm_planner is explicitly set to false.

	- When enabled, orchestrates retrieval using both local and global strategies (powers Deep Search)
	- When enabled (default), orchestrates retrieval using both local and global strategies (powers Deep Search)

DOC-790 | Importer & Retriever: Update startup parameters #809

DOC-790 | Importer & Retriever: Update startup parameters #809

Uh oh!

Conversation

nerpaula commented Oct 17, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Uh oh!

arangodb-docs-automation bot commented Oct 17, 2025

Uh oh!

This comment was marked as outdated.

Uh oh!

aMahanna left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

diegomendez40 left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

bluepal-pavan-kothapalli commented Oct 31, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

nerpaula commented Oct 31, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

cursor bot commented Oct 31, 2025

Uh oh!

nerpaula commented Nov 4, 2025

Uh oh!

diegomendez40 left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

diegomendez40 left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

nerpaula Nov 7, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

nerpaula commented Oct 17, 2025 •

edited

Loading

bluepal-pavan-kothapalli commented Oct 31, 2025 •

edited

Loading

nerpaula commented Oct 31, 2025 •

edited

Loading

nerpaula Nov 7, 2025 •

edited

Loading

bluepal-keerthi-datla Nov 7, 2025 •

edited

Loading

nerpaula Nov 7, 2025 •

edited

Loading