@vera-ai/cli 1.1.0 → 1.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +3 -3
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -4,7 +4,7 @@ Code search for AI agents. Vera indexes your codebase using tree-sitter parsing
|
|
|
4
4
|
|
|
5
5
|
This package downloads and wraps the native Vera binary for your platform. On musl-based Linux (Alpine, NixOS), the correct static binary is selected automatically. Set `VERA_TARGET` to override target detection (e.g., `VERA_TARGET=x86_64-unknown-linux-musl npm install -g @vera-ai/cli`).
|
|
6
6
|
|
|
7
|
-
The default local embedding model is `minishlab/potion-code-16M-v2
|
|
7
|
+
The default local embedding model is `minishlab/potion-code-16M-v2`; it runs locally on CPU on any supported machine, no GPU or ONNX Runtime needed. In the current Semble comparison, Vera v1.2.0 scored `0.8450` nDCG@10 versus Semble 0.5.5 at `0.8514`, using the same embeddings, harness, graded relevance, and suffix-corrected path matching. Full details live in the main repo docs.
|
|
8
8
|
|
|
9
9
|
## Install
|
|
10
10
|
|
|
@@ -19,7 +19,7 @@ vera setup --potion-code --index .
|
|
|
19
19
|
vera search "authentication logic"
|
|
20
20
|
```
|
|
21
21
|
|
|
22
|
-
`vera setup` with no flags runs an interactive wizard and offers to index the current project, defaulting to yes. An interactive search also offers to create a missing index. `vera setup --api` prompts for an OpenAI-compatible endpoint and key;
|
|
22
|
+
`vera setup` with no flags runs an interactive wizard and offers to index the current project, defaulting to yes. An interactive search also offers to create a missing index. `vera setup --api` prompts for an OpenAI-compatible endpoint and key; the wizard offers presets for OpenAI, Jina, Voyage, and Qwen via OpenRouter, with the Qwen preset needing only one shared key (`qwen/qwen3-embedding-8b` + `qwen/qwen3-reranker-8b` via `https://openrouter.ai/api/v1`). Use `--yes` with `EMBEDDING_MODEL_*` variables for non-interactive setup. `vera agent install` manages skill files for your coding agents and can update `AGENTS.md` / `CLAUDE.md` style project instructions.
|
|
23
23
|
|
|
24
24
|
## Common Tasks
|
|
25
25
|
|
|
@@ -48,7 +48,7 @@ For the full backend matrix, model options, Docker setup, and troubleshooting, s
|
|
|
48
48
|
|
|
49
49
|
## What you get
|
|
50
50
|
|
|
51
|
-
- **
|
|
51
|
+
- **65 languages** (61 with tree-sitter AST parsing)
|
|
52
52
|
- **Hybrid search**: BM25 keyword + vector similarity, fused with Reciprocal Rank Fusion
|
|
53
53
|
- **Opt-in cross-encoder reranking** for precision, disabled by default
|
|
54
54
|
- **Git-aware scopes and index debugging**: `--changed` / `--since` / `--base`, `explain-path`, and index health in `vera stats`
|