Skip to content

armgit / xerj

Public Imported from GitHub
0

AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

release: cut v1.0.0-rc.3

xerj-orgd9243e380bc4
diff --git a/CHANGELOG.md b/CHANGELOG.md
index b749994f8..f75bd8a19 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,46 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
+## [1.0.0-rc.3] - 2026-07-10
+
+Third release candidate. Headline: XERJ gains a **built-in neural embedder** —
+real in-process BERT semantics with no Python and no external service — behind a
+single backend-agnostic embedding handle, plus two new end-to-end-validated
+retrieval recipes.
+
+### Added
+
+- **Built-in neural BERT embedder (`xerj-ai`, feature `neural`).** A pure-Rust
+ sentence encoder via `candle` (default `all-MiniLM-L6-v2`, 384-dim) that runs
+ in-process and downloads its weights once on first use (or reads them from
+ `embedding.local_model_dir` for air-gapped deployments). Off by default so the
+ standard binary stays ~23 MB and dependency-light; build with
+ `cargo build --release -p xerj-server --features neural` to include it.
+- **Unified three-backend embedding handle (`xerj_ai::Embedder`).** `semantic_text`
+ ingest and `semantic`/`hybrid` queries run through one of three interchangeable
+ backends — **lexical** (default, zero-dep feature-hash), **neural** (built-in
+ BERT), or **proxy** (external OpenAI-compatible `/v1/embeddings`) — selected with
+ `embedding.mode`, the `--embed-mode` flag, or `XERJ_EMBED_MODE`. Misconfiguration
+ degrades to lexical, never a crash; `auto` preserves the historical behaviour.
+- **Recipe — All-you-can-eat search.** One corpus retrieved five ways from a single
+ index: full-text (BM25), semantic, vector kNN (more-like-this), hybrid (RRF), and
+ semantic-scoped-by-keyword-filter. Guide `docs/recipes/all-way-search.md`,
+ runnable `recipes/all_way_search.py`.
+- **Recipe — Zero-config folder → neural semantic search.** `xerj autoindex` a
+ mixed-format folder against a `--embed-mode neural` server, then search the
+ discovered prose by meaning while structured files stay exactly filterable. Guide
+ `docs/recipes/autoindex-semantic-search.md`, runnable `recipes/autoindex_semantic.sh`,
+ sample corpus `demo/data/support-folder/`.
+
+### Changed
+
+- `--embed-mode {lexical|neural|proxy|auto}` CLI flag and `XERJ_EMBED_MODE` env on
+ the server; new `embedding.{mode,neural_model,model_cache_dir,local_model_dir}`
+ config keys.
+- Documentation updated for honesty consistency (README, AGENTS.md, ROADMAP.md,
+ llms.txt, recipe guides): the **default** embedder is lexical; the neural embedder
+ is an **opt-in** upgrade — output is only described as neural when that mode runs.
+
## [1.0.0-rc.1] - 2026-07-06
First public release candidate of XERJ — an Elasticsearch-wire-compatible search,
diff --git a/engine/Cargo.lock b/engine/Cargo.lock
index d181f4788..7163bccf7 100644
--- a/engine/Cargo.lock
+++ b/engine/Cargo.lock
@@ -5018,7 +5018,7 @@ dependencies = [
[[package]]
name = "xerj-ai"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"candle-core",
@@ -5037,7 +5037,7 @@ dependencies = [
[[package]]
name = "xerj-api"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"async-trait",
@@ -5066,7 +5066,7 @@ dependencies = [
[[package]]
name = "xerj-autoindex"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"chrono",
@@ -5090,7 +5090,7 @@ dependencies = [
[[package]]
name = "xerj-cluster"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"async-trait",
@@ -5112,7 +5112,7 @@ dependencies = [
[[package]]
name = "xerj-common"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"byteorder",
@@ -5129,7 +5129,7 @@ dependencies = [
[[package]]
name = "xerj-compress"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"byteorder",
"bytes",
@@ -5142,7 +5142,7 @@ dependencies = [
[[package]]
name = "xerj-console-api"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"arc-swap",
@@ -5178,7 +5178,7 @@ dependencies = [
[[package]]
name = "xerj-engine"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"arc-swap",
@@ -5217,7 +5217,7 @@ dependencies = [
[[package]]
name = "xerj-fts"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"bitpacking",
@@ -5243,7 +5243,7 @@ dependencies = [
[[package]]
name = "xerj-logs"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"byteorder",
@@ -5261,7 +5261,7 @@ dependencies = [
[[package]]
name = "xerj-mcp"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"reqwest",
@@ -5271,7 +5271,7 @@ dependencies = [
[[package]]
name = "xerj-query"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"base64 0.22.1",
@@ -5286,7 +5286,7 @@ dependencies = [
[[package]]
name = "xerj-server"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"axum",
@@ -5327,7 +5327,7 @@ dependencies = [
[[package]]
name = "xerj-storage"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"arc-swap",
@@ -5356,7 +5356,7 @@ dependencies = [
[[package]]
name = "xerj-vector"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"byteorder",
@@ -5374,7 +5374,7 @@ dependencies = [
[[package]]
name = "xerj-wasm"
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
dependencies = [
"anyhow",
"bytes",
diff --git a/engine/Cargo.toml b/engine/Cargo.toml
index 3f96c9f0b..116232fb2 100644
--- a/engine/Cargo.toml
+++ b/engine/Cargo.toml
@@ -21,7 +21,7 @@ members = [
]
[workspace.package]
-version = "1.0.0-rc.2"
+version = "1.0.0-rc.3"
edition = "2021"
license = "Apache-2.0"
authors = ["xerj Contributors"]