Retrieval

OpenViking provides multiple retrieval methods, including simple vector similarity search, intelligent retrieval with session context, regex pattern matching, and file pattern matching.

find vs search

Aspect	find	search
Intent Analysis	No	Yes
Session Context	No	Yes
Query Expansion	No	Yes
Default Limit	10	10
Use Case	Simple queries	Conversational search

Retrieval Pipeline

The core retrieval pipeline is as follows:

Query → Intent Analysis (search only) → Vector Search (L0) → Rerank (L1) → Results

Intent Analysis (search only): Understand query intent, expand queries
Vector Search: Find candidates using embeddings
Rerank: Re-score using content for better accuracy
Results: Return top-k contexts

API Reference

find()

Basic vector similarity search without session context.

1. API Implementation Introduction

The find() method performs pure vector similarity search for simple query scenarios. It uses hierarchical retrieval to search at the L0 summary level first, then matches in detail at L1/L2 levels.

Processing Pipeline:

Convert query text to vector
Perform global vector search within specified target URI
Use hierarchical retrieval strategy to recursively search relevant directories and files
Optional: Use rerank model to optimize result ordering
Return matched context list

Code Entry Points:

openviking_cli/client/sync_http.py:SyncHTTPClient.find() - Python SDK entry (HTTP)
openviking/retrieve/hierarchical_retriever.py:HierarchicalRetriever.retrieve() - Core retrieval implementation
openviking/server/routers/search.py:find() - HTTP router
crates/ov_cli/src/commands/search.rs:find() - Rust CLI command

2. Interface and Parameter Description

Parameters

Parameter	Type	Required	Default	Description
query	str	No	""	Search query string. Required unless `image_url` is provided
image_url	str	No	None	Image query as a `data:image/...;base64,...`, `http(s)://`, or `viking://` URI. Requires a multimodal embedding model
target_uri	str \| List[str]	No	""	Limit search to specific URI prefix
context_type	str \| List[str]	No	None	Limit results to one or more `ContextType` values: `memory`, `resource`, or `skill`
tags	List[str]	No	None	Explicit retrieval tags in strict `k=v` form. Multiple tags are combined with AND; a result must contain every requested tag
node_limit	int	No	None	Maximum number of results
score_threshold	float	No	None	Minimum relevance score threshold
filter	Dict	No	None	Metadata filter
since	str	No	None	Lower time bound, accepts `2h` or ISO 8601 / `YYYY-MM-DD`. Timezone-less values are interpreted as UTC. CLI `--after` maps to this field
until	str	No	None	Upper time bound, accepts `30m` or ISO 8601 / `YYYY-MM-DD`. Timezone-less values are interpreted as UTC. CLI `--before` maps to this field
time_field	"updated_at" \| "created_at"	No	"updated_at"	Metadata time field used by `since` / `until`
level	str	No	None	Limit results to specific level(s), e.g., `0`, `1`, `2`, or `0,1,2`. CLI `--level`/`-L` maps to this field
include_provenance	bool	No	False	Include provenance/query-plan details in serialized result
telemetry	bool \| object	No	False	Attach telemetry data to response

Target resolution notes:

With empty target_uri, non-ROOT retrieval searches the current user root (viking://user/{user}) and shared viking://resources.
To filter the current user's peer collection to one peer for filesystem and retrieval operations, send X-OpenViking-Actor-Peer: <peer_id> or construct the SDK/CLI client with actor_peer_id. See Multi-Tenant: Peer Collection Filter.
Current-user shorthand target URIs such as viking://user/memories, viking://user/resources, and viking://user/skills are canonicalized from the authenticated request identity.

Image search notes:

Image queries use the image vector as the query and search L2 resource leaf nodes in the target scope by default. Results are not limited to image files; multimodal embedding decides similarity between the query image and text/image resources.
Text-only embedding models still index image summaries, but image query input is rejected.
Existing image resources keep their existing vectors; image-vector recall applies to images vectorized after this capability is enabled or after a later reindex.

FindResult Structure

python

class FindResult:
    memories: List[MatchedContext]   # Memory contexts
    resources: List[MatchedContext]  # Resource contexts
    skills: List[MatchedContext]     # Skill contexts
    query_plan: Optional[QueryPlan]  # Query plan (search only)
    query_results: Optional[List[QueryResult]]  # Detailed results
    total: int                       # Total count (auto-calculated)

MatchedContext Structure

python

class MatchedContext:
    uri: str                         # Viking URI
    context_type: ContextType        # "resource", "memory", or "skill"
    level: int                       # Tier (0=L0, 1=L1, 2=L2)
    abstract: str                    # L0 content
    overview: Optional[str]          # L1 overview (optional for non-leaf nodes)
    category: str                    # Category
    score: float                     # Relevance score (0-1)
    match_reason: str                # Why this matched
    relations: List[RelatedContext]  # Related contexts

3. Usage Examples

HTTP API

POST /api/v1/search/find

bash

curl -X POST http://localhost:1933/api/v1/search/find \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "query": "how to authenticate users",
        "limit": 10
    }'

Search with Target URI and Time Filter

bash

curl -X POST http://localhost:1933/api/v1/search/find \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "query": "authentication",
        "target_uri": "viking://resources",
        "since": "7d",
        "time_field": "created_at"
    }'

Search by Context Type

bash

curl -X POST http://localhost:1933/api/v1/search/find \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "query": "authentication",
        "context_type": ["memory", "resource"]
}'

Image Search

bash

curl -X POST http://localhost:1933/api/v1/search/find \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "image_url": "viking://resources/images/cat.png",
        "limit": 10
    }'

Search by Explicit Retrieval Tags

bash

curl -X POST http://localhost:1933/api/v1/search/find \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "query": "rollback runbook",
        "tags": ["env=prod", "team=search"]
    }'

Tags must use strict k=v strings. When multiple tags are provided, find() requires all of them; the example above only returns contexts whose explicit retrieval tags contain both env=prod and team=search.

Python SDK

python

import openviking as ov
from openviking.retrieve import ContextType

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

# Basic search
results = client.find("how to authenticate users")

# Search with filter and time range
recent_emails = client.find(
    "invoice",
    target_uri="viking://resources/email",
    since="7d",
    time_field="created_at",
)

# Search only memories and resources
typed_results = client.find(
    "authentication",
    context_type=[ContextType.MEMORY, ContextType.RESOURCE],
)

# Search by local image, bytes, data URI, HTTP URL, or viking:// URI
image_results = client.find(image="/path/to/photo.png")

# Search by explicit retrieval tags. Multiple tags are AND-ed.
tagged_results = client.find(
    "rollback runbook",
    tags=["env=prod", "team=search"],
)

# Iterate through results
for ctx in results.resources:
    print(f"URI: {ctx.uri}")
    print(f"Score: {ctx.score:.3f}")
    print(f"Type: {ctx.context_type}")
    print(f"Abstract: {ctx.abstract[:100]}...")
    print("---")

Search with Target URI Limitation

python

# Search only in resources
results = client.find(
    "authentication",
    target_uri="viking://resources"
)

# Search only in user memories
results = client.find(
    "preferences",
    target_uri="viking://user/memories"
)

# Search only in current-user resources
results = client.find(
    "private docs",
    target_uri="viking://user/resources"
)

# Search with the peer collection filtered to one peer
peer_client = ov.SyncHTTPClient(
    url="http://localhost:1933",
    api_key="your-key",
    actor_peer_id="web-visitor-alice",
)
peer_results = peer_client.find("invoice follow-up")

# Search only in skills
results = client.find(
    "web search",
    target_uri="viking://user/skills"
)

# Search in specific project
results = client.find(
    "API endpoints",
    target_uri="viking://resources/my-project"
)

TypeScript SDK

typescript

console.log(await client.find("authentication", { targetUri: "viking://resources/docs/" }));

Go SDK

result, err := client.Find(ctx, "how to authenticate users", &openviking.FindOptions{
    TargetURI:   "viking://resources/docs",
    Limit:       10,
    ContextType: []string{"resource"},
})
if err != nil {
    return err
}
for _, item := range result.Resources {
    fmt.Println(item.URI, item.Score)
}

CLI

bash

# Basic search
openviking find "how to authenticate users"

# Specify URI scope
openviking find "how to authenticate users" --uri "viking://resources"

# Limit to context types
openviking find "authentication" --context-type memory,resource

# With time filter
openviking find "invoice" --after 7d

# With limit
openviking find "how to authenticate users" --limit 20

# Limit to specific level(s) (L0 only)
openviking find "how to authenticate users" --level 0

# Limit to specific level(s) (L1 and L2) using short option
openviking find "how to authenticate users" -L 1,2

# Image queries use only --image; pass a local path, viking://, http(s)://, or data:image URI
openviking find --image ./query.png --uri "viking://resources/images" --limit 5

# Search by an image already stored in VikingFS
openviking find --image "viking://resources/images/cat.png" --uri "viking://resources/images" --limit 5

# Search by a public image URL
openviking find --image "https://example.com/images/cat.png" --uri "viking://resources/images" --limit 5

# Combine text and image
openviking find "red poster style" --image ./poster.png --uri "viking://resources/images"

Response Example

json

{
    "status": "ok",
    "result": {
        "memories": [],
        "resources": [
            {
                "context_type": "resource",
                "uri": "viking://resources/01-overview/API_Overview/Documentation_Reading_P_2c6ae38b.md",
                "level": 2,
                "score": 0.12808319406977778,
                "category": "",
                "match_reason": "",
                "relations": [],
                "abstract": "This document is an API documentation reading plan that outlines the structure of subsequent API reference materials organized by functional module. Main sections or topics covered include resource management API, search API, file system operations, ses...",
                "overview": null
            },
            {
                "context_type": "resource",
                "uri": "viking://resources/01-overview/API_Overview/API_Endpoints/.abstract.md",
                "level": 0,
                "score": 0.12054087276495282,
                "category": "",
                "match_reason": "",
                "relations": [],
                "abstract": "This directory contains structured API reference documentation for the OpenViking platform, compiling detailed HTTP endpoint specifications for core and extended platform capabilities. It covers functional modules including system health checks, semanti...",
                "overview": null
            }
        ],
        "skills": [],
        "total": 2
    }
}

search()

Intelligent retrieval with session context and intent analysis.

1. API Implementation Introduction

The search() method adds session context understanding and intent analysis capability on top of find(). It better understands user query intent based on conversation history, performs query expansion, and provides more relevant search results.

Processing Pipeline:

Load session context (if session_id is provided)
Analyze query intent, understand actual needs combined with conversation history
Expand queries to improve recall rate
Execute same hierarchical retrieval pipeline as find()
Return search results with query plan

Code Entry Points:

openviking_cli/client/sync_http.py:SyncHTTPClient.search() - Python SDK entry (HTTP)
openviking/retrieve/hierarchical_retriever.py:HierarchicalRetriever.retrieve() - Core retrieval implementation
openviking/server/routers/search.py:search() - HTTP router
crates/ov_cli/src/commands/search.rs:search() - Rust CLI command

2. Interface and Parameter Description

Parameters

Parameter	Type	Required	Default	Description
query	str	No	""	Search query string. Required unless `image_url` is provided
image_url	str	No	None	Image query as a `data:image/...;base64,...`, `http(s)://`, or `viking://` URI. Requires a multimodal embedding model
target_uri	str \| List[str]	No	""	Limit search to specific URI prefix
session	Session	No	None	Session for context-aware search (SDK)
session_id	str	No	None	Session ID for context-aware search (HTTP)
context_type	str \| List[str]	No	None	Limit results to one or more `ContextType` values: `memory`, `resource`, or `skill`
tags	List[str]	No	None	Explicit retrieval tags in strict `k=v` form. Multiple tags are combined with AND; a result must contain every requested tag
node_limit	int	No	None	Maximum number of results
score_threshold	float	No	None	Minimum relevance score threshold
filter	Dict	No	None	Metadata filter
since	str	No	None	Lower time bound, accepts `2h` or ISO 8601 / `YYYY-MM-DD`. Timezone-less values are interpreted as UTC. CLI `--after` maps to this field
until	str	No	None	Upper time bound, accepts `30m` or ISO 8601 / `YYYY-MM-DD`. Timezone-less values are interpreted as UTC. CLI `--before` maps to this field
time_field	"updated_at" \| "created_at"	No	"updated_at"	Metadata time field used by `since` / `until`
level	str	No	None	Limit results to specific level(s), e.g., `0`, `1`, `2`, or `0,1,2`. CLI `--level`/`-L` maps to this field
include_provenance	bool	No	False	Include provenance/query-plan details in serialized result
telemetry	bool \| object	No	False	Attach telemetry data to response

search() uses the same target resolution and explicit tag filtering rules as find(), including the peer collection filter selected by X-OpenViking-Actor-Peer or SDK actor_peer_id. When image_url is provided, search() uses direct image retrieval and skips session query planning.

3. Usage Examples

HTTP API

POST /api/v1/search/search

bash

curl -X POST http://localhost:1933/api/v1/search/search \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "query": "best practices",
        "session_id": "abc123",
        "context_type": "skill",
        "since": "2h",
        "time_field": "updated_at",
        "limit": 10
    }'

Search without Session (Still Performs Intent Analysis)

bash

curl -X POST http://localhost:1933/api/v1/search/search \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "query": "how to implement OAuth 2.0 authorization code flow"
}'

Image Search

bash

curl -X POST http://localhost:1933/api/v1/search/search \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "query": "similar poster",
        "image_url": "data:image/png;base64,...",
        "limit": 10
    }'

Python SDK

python

import openviking as ov
from openviking.retrieve import ContextType
from openviking.message import TextPart

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

# Create session with conversation context
session = client.session()
session.add_message("user", [
    TextPart(text="I'm building a login page with OAuth")
])
session.add_message("assistant", [
    TextPart(text="I can help you with OAuth implementation.")
])

# Search understands conversation context
results = client.search(
    "best practices",
    session=session,
    context_type=ContextType.SKILL,
    since="2h"
)

for ctx in results.resources:
    print(f"Found: {ctx.uri}")
    print(f"Abstract: {ctx.abstract[:200]}...")

Search without Session

python

# search can also be used without session
# It still performs intent analysis on the query
results = client.search(
    "how to implement OAuth 2.0 authorization code flow"
)

for ctx in results.resources:
    print(f"Found: {ctx.uri} (score: {ctx.score:.3f})")

Image Search

python

results = client.search("similar poster", image="/path/to/poster.png")

TypeScript SDK

typescript

console.log(await client.search("authentication", { targetUri: "viking://resources/docs/" }));

Go SDK

result, err := client.Search(ctx, "best practices", &openviking.SearchOptions{
    SessionID:   "abc123",
    ContextType: "skill",
    Limit:       10,
})
if err != nil {
    return err
}
fmt.Println(result.Total)

CLI

bash

# Search with session ID
openviking search "best practices" --session-id abc123

# Limit to a context type
openviking search "best practices" --context-type skill

# Search with time filter
openviking search "watch vs scheduled" --after 2026-03-15 --before 2026-03-20

# Search without session (still performs intent analysis)
openviking search "how to implement OAuth 2.0 authorization code flow"

# Limit to specific level(s) (L0 only)
openviking search "best practices" --level 0

# Limit to specific level(s) (L1 and L2) using short option
openviking search "how to implement OAuth" -L 1,2

# Image queries also use --image; they use direct retrieval and skip session planning
openviking search "similar poster" --image ./poster.png --uri "viking://resources/images"

Response Example

json

{
    "status": "ok",
    "result": {
        "memories": [],
        "resources": [
            {
                "context_type": "resource",
                "uri": "viking://resources/docs/oauth-best-practices",
                "level": 1,
                "score": 0.95,
                "category": "",
                "match_reason": "Context-aware match: OAuth login best practices",
                "relations": [],
                "abstract": "OAuth 2.0 best practices for login pages...",
                "overview": "This guide covers OAuth 2.0 best practices including secure token handling, redirect URI validation, and state parameter usage..."
            }
        ],
        "skills": [],
        "query_plan": {
            "reasoning": "User is asking about OAuth implementation best practices, expanding to related security topics",
            "queries": [
                {
                    "query": "OAuth 2.0 best practices",
                    "context_type": "resource",
                    "intent": "Find OAuth 2.0 implementation guidelines",
                    "priority": 3
                },
                {
                    "query": "login page security",
                    "context_type": "resource",
                    "intent": "Find login page security recommendations",
                    "priority": 2
                }
            ]
        },
        "total": 1
    }
}

search(mode="context")

Assemble retrieval results into an injection-ready context block. mode="list" (the default) returns the ranked hit list and behaves exactly like the previous search(); mode="context" opens the assembly face: budgeting, tier degradation, cross-turn dedup and the optional LLM digest all happen server-side in one request.

1. Implementation Overview

Injecting context every turn used to mean searching per type, reading each hit back, and stitching the block together client-side. With assembly on the server, a plugin sends one request and every harness shares one budgeting, degradation and dedup implementation.

Pipeline:

L1 query understanding: optional bounded intent expansion from the session's recent messages (at most 3 queries, timeout fuse, falls back to the original query)
L0 retrieval: bucketed per quotas, or a single whole-scope search when quotas are off
L2 assembly: tier filling inside the token budget (everyone at their category's default tier first, then leftover budget deepens in score order); an oversized tier falls back instead of being truncated
L3 rewrite: optional digest with URI citations (timeout fuse; on failure the unrewritten rendered is still returned; an exact NO_RELEVANT_MEMORY result is reported as stats.rewrite="no_relevant" so Coding Agent clients inject nothing instead of falling back to rendered)

Code entry points:

openviking/server/routers/search.py:_search_context() - HTTP route branch
openviking/retrieve/context_assembler/pipeline.py:assemble_context() - assembly orchestration
openviking/retrieve/context_assembler/budget.py:plan_entries() - budgeting and tier filling
openviking/retrieve/context_assembler/tiers.py - overview extraction per source type

2. Parameters

L0 retrieval domain: query, image_url, context_type, limit, score_threshold, filter, tags, since/until behave as in list mode. limit applies only to quota-free retrieval. Once purpose or explicit quotas enables bucketed retrieval, the per-category quotas are the only candidate ceilings. target_uri is not supported in context mode yet (returns 400); level is ignored because detail governs tiers.

L1 query understanding

Parameter	Type	Default	Description
`session_id`	str	None	Required to enable query expansion and server-side dedup
`query_expansion`	`off` \| `auto`	`auto`	Bounded session-aware expansion; falls back to the original query without a session or on failure

L2 assembly

Parameter	Type	Default	Description
`limit`	int	10	Candidate ceiling for quota-free retrieval only; ignored when `purpose` or `quotas` enables bucketed retrieval
`max_tokens`	int	1600	The single budget parameter, estimated with a CJK-aware heuristic (codepoint ≥ 0x3000 counts 1.5 tok/char, otherwise chars/4)
`quotas`	object	None	Absolute per-bucket limits; keys are `events`/`entities`/`preferences`/`experiences`/`resources`/`skills`. Explicit quotas ignore `limit`
`purpose`	`chat` \| `coding`	None	Enables six-domain bucket sampling with the absolute preset quotas below. Applies only when `quotas` is not given
`detail`	`abstract` \| `overview` \| `full` \| object	None	Requests one starting/maximum tier for every entry. Entries whose requested tier is unavailable or does not fit step down instead of being truncated. Omitted, each category takes its default tier (below). Also accepts a per-category object such as `{"events":"overview","preferences":"abstract"}`; categories left out keep their default. `"auto"` is a deprecated spelling and behaves as if omitted
`dedup_turns`	int	0	Cooldown window in turns; needs `session_id`. Ledger lives at `{session_uri}/.recall_log.json`
`exclude_uris`	string[]	[]	Stateless dedup fallback, up to 200 entries, unioned with `dedup_turns`
`peer_scope`	`actor` \| `all`	`all`	`actor` excludes other peers while keeping global, self-owned and current-actor content
`other_peer_penalty`	number \| object	per-category defaults	Score penalty applied to other-peer hits

L3 rewrite

Parameter	Type	Default	Description
`rewrite`	bool \| `auto`	`false`	Server-side digest rewrite; `auto` engages only when a query_planner model is configured
`rewrite_max_bullets`	int	6	Digest bullet ceiling (1–20)

Tier rules

Purpose presets: chat uses events:3, entities:3, preferences:1, experiences:1, resources:1, skills:1; coding uses events:1, entities:2, preferences:1, experiences:1, resources:3, skills:2. These are absolute per-category ceilings, not weights. Results are deduplicated and globally sorted after gathering, but are not truncated by a second global limit

Default tier per category: with detail omitted, each category lands on the tier below. Only events reads a file; every other category costs no read

Category	Default tier	Leftover budget may reach	Why
`events`	overview	full	The one memory type whose body is long enough for `# Summary` extraction to be a real compression
`entities` / `preferences` / `experiences`	abstract	abstract	Short bodies, and the writer stores the whole body in the abstract scalar, so abstract already is the complete file
`resources` / `skills`	abstract	abstract	The 256-char abstract from semantic processing; bodies can be large or carry credentials, so deepening is opt-in
`memories`	abstract	abstract	Built-in memory types outside the four named ones — `cases`, `patterns`, `tools`, `trajectories`, skill-usage memories. Only quota-free retrieval reaches them; they own no bucket, so `quotas` cannot name them, but `detail` and `other_peer_penalty` can
Directory hits	overview	overview	A directory has no abstract, so it reads the `.overview.md` sidecar; a full tier is meaningless for a subtree

Floor: every result carries at least its uri. When a memory abstract is unavailable or busts the per-entry cap, the entry falls back to overview: the memory writer stores the whole body in that scalar, so for memory categories overview sits below abstract on the content ladder and the substitute discloses less. A resources or skills abstract is the short generated summary instead, so the same substitution would read a body the caller never asked for — those two degrade to a bare uri rather than deepen
Explicit detail: sets that tier as both the requested start and ceiling; entries that do not fit still step down a tier rather than being truncated. The memory overview substitute above is the one case where the served detail can outrank the pin, and only because it carries less content than the pinned tier would
Overview by source type: memory files use the leading # Summary section, code files use class and function signatures (reusing code_outline), long documents use the heading tree plus first paragraph
Per-entry cap: max_tokens ÷ candidate_count × 2, applied to every tier except the bare uri; a tier exceeding it falls back to the previous tier rather than being truncated. If budget is still left over, one final deepening pass ignores the cap and is bounded only by max_tokens

3. Examples

HTTP API

bash

# Basic context assembly
curl -X POST http://localhost:1933/api/v1/search/search \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENVIKING_API_KEY" \
  -d '{"query":"what changed on this branch","mode":"context","max_tokens":1600}'

# Session-aware: query expansion plus cross-turn dedup
curl -X POST http://localhost:1933/api/v1/search/search \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENVIKING_API_KEY" \
  -d '{
    "query":"continue that refactor",
    "mode":"context",
    "session_id":"cc-1a2b3c",
    "query_expansion":"auto",
    "dedup_turns":5,
    "purpose":"coding",
    "max_tokens":3000
  }'

# With the server-side digest rewrite
curl -X POST http://localhost:1933/api/v1/search/search \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENVIKING_API_KEY" \
  -d '{"query":"tier design","mode":"context","max_tokens":3000,"rewrite":true}'

Response

json

{
  "status": "ok",
  "result": {
    "entries": [
      {
        "uri": "viking://user/default/memories/events/2026/07/14/tier_design.md",
        "category": "events",
        "score": 0.45,
        "detail": "full",
        "text": "# Summary\nTiers now take a per-category default\n...",
        "origin": "self"
      },
      {
        "uri": "viking://user/default/memories/entities/software/openviking_fs.md",
        "category": "entities",
        "score": 0.43,
        "detail": "abstract",
        "text": "OpenViking FS storage layer...",
        "origin": "self"
      }
    ],
    "rendered": "<memory uri=\"viking://user/default/memories/events/2026/07/14/tier_design.md\" type=\"events\" score=\"0.45\" detail=\"full\">\n# Summary\n...\n</memory>",
    "digest": "",
    "stats": {
      "candidates": 13,
      "returned": 13,
      "dropped": 0,
      "deduped": 0,
      "max_tokens": 3000,
      "used_tokens": 2510,
      "per_entry_cap": 462,
      "detail": null,
      "tier_counts": {"full": 4, "overview": 2, "abstract": 7},
      "fill": {"floor_tokens": 1890, "overview_upgrades": 0, "full_upgrades": 4, "spare_upgrades": 0},
      "query_expansion": "used",
      "rewrite": "off",
      "rewrite_usage": null,
      "excluded": 0,
      "dedup": {"turns": 5, "status": "ok", "cooled": 2, "turn": 34}
    }
  }
}

Field	Type	Description
`entries[].uri`	string	Entry URI, always present at every tier, expandable with the MCP `read` tool
`entries[].category`	string	`events`/`entities`/`preferences`/`experiences`/`resources`/`skills`, or `memories` for a built-in memory type outside those four
`entries[].detail`	string	Tier actually served: `full`, `overview`, `abstract` or `uri`
`entries[].text`	string	Body for that tier; empty at the `uri` tier
`rendered`	string	Flat XML context block, ready to inject; empty when rewrite reports `no_relevant`
`digest`	string	Digest when the rewrite succeeded, empty string on failure or when the compressor reports no relevant memory
`stats`	object	Budget usage, tier distribution, expansion and rewrite status (`off`, `ok`, `no_relevant`, `failed` or `timeout`), dedup ledger state; carries `retrieval_errors` when a retrieval scope failed, so a broken index is distinguishable from having no relevant memories

When stats.rewrite is no_relevant, the response keeps entries for inspection but returns both digest and rendered as empty strings. This makes the successful empty result safe for clients that predate the explicit status. Nothing was served that turn, so those URIs also stay out of the dedup_turns ledger and remain available to the later turn they are relevant to.

Validation rules

Any context-only parameter sent explicitly under mode="list" → 400
target_uri under mode="context" → 400
Unknown quotas key → 400
Fields ignored in context mode (level, and limit when purpose or explicit quotas are active) are reported in stats.ignored

grep()

Search content by pattern (regex).

1. API Implementation Introduction

The grep() method performs regex pattern matching search in the file system, used to find files and content lines containing specific patterns. Unlike semantic search, grep is exact pattern matching.

Processing Pipeline:

Traverse file system starting from specified URI
Perform regex matching on each file content
Collect matching lines and position information
Return matching results list

Code Entry Points:

openviking_cli/client/sync_http.py:SyncHTTPClient.grep() - Python SDK entry (HTTP)
openviking/server/routers/search.py:grep() - HTTP router
crates/ov_cli/src/commands/search.rs:grep() - Rust CLI command

2. Interface and Parameter Description

Parameters

Parameter	Type	Required	Default	Description
uri	str	Yes	-	Viking URI to search in
pattern	str	Yes	-	Search pattern (regex)
case_insensitive	bool	No	False	Ignore case
exclude_uri	str	No	None	URI prefix to exclude from search
node_limit	int	No	256	Maximum number of results. Omitted requests default to 256; pass a larger integer when you need more results
level_limit	int	No	Python SDK: 5; HTTP API / CLI / Go SDK: 10	Maximum directory depth to traverse. The Go SDK currently uses the HTTP API default.

3. Usage Examples

HTTP API

POST /api/v1/search/grep

bash

curl -X POST http://localhost:1933/api/v1/search/grep \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "uri": "viking://resources",
        "pattern": "authentication",
        "case_insensitive": true
    }'

Python SDK

python

import openviking as ov

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

results = client.grep(
    "viking://resources",
    "authentication",
    case_insensitive=True,
    node_limit=1024,
)

print(f"Found {results['count']} matches")
for match in results['matches']:
    print(f"  {match['uri']}:{match['line']}")
    print(f"    {match['content']}")

TypeScript SDK

typescript

console.log(await client.grep("viking://resources/docs/", "authentication"));

Go SDK

nodeLimit := 1024
result, err := client.Grep(ctx, "viking://resources", "authentication", &openviking.GrepOptions{
    CaseInsensitive: true,
    NodeLimit:       &nodeLimit,
})
if err != nil {
    return err
}
fmt.Println(result["count"])

CLI

bash

# Basic search
openviking grep "authentication" --uri viking://resources

# Ignore case
openviking grep "authentication" --uri viking://resources --ignore-case

# Specify depth limit
openviking grep "TODO" --uri viking://resources --level-limit 3

Response Example

json

{
    "status": "ok",
    "result": {
        "matches": [
            {
                "uri": "viking://resources/docs/auth.md",
                "line": 15,
                "content": "User authentication is handled by..."
            }
        ],
        "count": 1
    },
    "time": 0.1
}

glob()

Match files by glob pattern.

1. API Implementation Introduction

The glob() method uses file wildcard pattern matching URIs, similar to Unix shell glob functionality. Used to find files and directories by name patterns.

Supported Pattern Syntax:

* matches any character (except path separator)
** recursively matches any directory
? matches single character
[] matches character range

Code Entry Points:

sdk/python/openviking_sdk/client.py:SyncHTTPClient.glob() - Python SDK entry (HTTP)
openviking/server/routers/search.py:glob() - HTTP router
crates/ov_cli/src/commands/search.rs:glob() - Rust CLI command

2. Interface and Parameter Description

Parameters

Parameter	Type	Required	Default	Description
pattern	str	Yes	-	Glob pattern (e.g., `*/.md`)
uri	str	No	"viking://"	Starting URI
node_limit	int	No	256	Maximum number of matches to return. Omitted requests default to 256; pass a larger integer when you need more results

3. Usage Examples

HTTP API

POST /api/v1/search/glob

bash

curl -X POST http://localhost:1933/api/v1/search/glob \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{
        "pattern": "**/*.md",
        "uri": "viking://resources"
    }'

Python SDK

python

import openviking as ov

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

# Find all markdown files (defaults to returning at most 256 matches)
results = client.glob("**/*.md", "viking://resources")
print(f"Found {results['count']} markdown files:")
for uri in results['matches']:
    print(f"  {uri}")

# Find all Python files with a higher explicit cap
results = client.glob("**/*.py", "viking://resources", node_limit=1024)
print(f"Found {results['count']} Python files")

TypeScript SDK

typescript

console.log(await client.glob("**/*.md", "viking://resources/docs/"));

Go SDK

result, err := client.Glob(ctx, "**/*.md", "viking://resources", &openviking.GlobOptions{
    NodeLimit: openviking.Int(1024),
})
if err != nil {
    return err
}
fmt.Println(result["count"])

CLI

bash

# Find all markdown files
openviking glob "**/*.md" --uri viking://resources

# Find all Python files
openviking glob "**/*.py"

Response Example

json

{
    "status": "ok",
    "result": {
        "matches": [
            "viking://resources/docs/api.md",
            "viking://resources/docs/guide.md"
        ],
        "count": 2
    },
    "time": 0.1
}

Working with Results

Read Content Progressively

Retrieval results usually only contain L0 summaries, you can progressively load more detailed content as needed.

Python SDK

python

import openviking as ov

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

results = client.find("authentication")

for ctx in results.resources:
    # Start with L0 (abstract) - already in ctx.abstract
    print(f"Abstract: {ctx.abstract}")

    if ctx.level < 2:
        # Get L1 (overview) for directories
        overview = client.overview(ctx.uri)
        print(f"Overview: {overview[:500]}...")
    else:
        # Load L2 (content) for files
        content = client.read(ctx.uri)
        print(f"File content: {content}")

HTTP API

bash

# Step 1: Search
curl -X POST http://localhost:1933/api/v1/search/find \
    -H "Content-Type: application/json" \
    -H "X-API-Key: your-key" \
    -d '{"query": "authentication"}'

# Step 2: Read overview for directory result
curl -X GET "http://localhost:1933/api/v1/content/overview?uri=viking://resources/docs/auth" \
    -H "X-API-Key: your-key"

# Step 3: Read full content for file result
curl -X GET "http://localhost:1933/api/v1/content/read?uri=viking://resources/docs/auth.md" \
    -H "X-API-Key: your-key"

Python SDK

python

import openviking as ov

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

results = client.find("OAuth implementation")

for ctx in results.resources:
    print(f"Found: {ctx.uri}")

    # Get related resources
    relations = client.relations(ctx.uri)
    for rel in relations:
        print(f"  Related: {rel['uri']} - {rel['reason']}")

HTTP API

bash

# Get relations for resource
curl -X GET "http://localhost:1933/api/v1/relations?uri=viking://resources/docs/auth" \
    -H "X-API-Key: your-key"

Best Practices

Use Specific Queries

python

import openviking as ov

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

# Good - specific query
results = client.find("OAuth 2.0 authorization code flow implementation")

# Less effective - too broad
results = client.find("auth")

Scope Your Searches

python

import openviking as ov

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

# Search in relevant scope for better results
results = client.find(
    "error handling",
    target_uri="viking://resources/my-project"
)

Use Session Context for Conversations

python

import openviking as ov
from openviking.message import TextPart

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

# For conversational search, use session
session = client.session()
session.add_message("user", [
    TextPart(text="I'm building a login page")
])

# Search understands context
results = client.search("best practices", session=session)

Resources - Resource management
Sessions - Session context
Context Layers - L0/L1/L2

Retrieval

Retrieval

find vs search

Retrieval Pipeline

API Reference

find()

1. API Implementation Introduction

2. Interface and Parameter Description

3. Usage Examples

search()

1. API Implementation Introduction

2. Interface and Parameter Description

3. Usage Examples

search(mode="context")

1. Implementation Overview

2. Parameters

3. Examples

grep()

1. API Implementation Introduction

2. Interface and Parameter Description

3. Usage Examples

glob()

1. API Implementation Introduction

2. Interface and Parameter Description

3. Usage Examples

Working with Results

Read Content Progressively

Get Related Resources

Best Practices

Use Specific Queries

Scope Your Searches

Use Session Context for Conversations

Related Documentation