deeprefine-cli 0.1.4__tar.gz → 0.1.5__tar.gz
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.
- {deeprefine_cli-0.1.4/deeprefine_cli.egg-info → deeprefine_cli-0.1.5}/PKG-INFO +22 -13
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/README.md +21 -12
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/SKILL.md +12 -4
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5/deeprefine_cli.egg-info}/PKG-INFO +22 -13
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/SKILL.md +12 -4
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/__init__.py +1 -1
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/pyproject.toml +1 -1
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/LICENSE +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/MANIFEST.in +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/SOURCES.txt +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/dependency_links.txt +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/entry_points.txt +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/requires.txt +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_cli.egg-info/top_level.txt +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/adapter_graphify.py +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/cli.py +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/history.py +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/installers.py +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/paths.py +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/deeprefine_skill/refine_runner.py +0 -0
- {deeprefine_cli-0.1.4 → deeprefine_cli-0.1.5}/setup.cfg +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: deeprefine-cli
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.5
|
|
4
4
|
Summary: CLI and Cursor skill to refine graphify knowledge graphs with DeepRefine
|
|
5
5
|
Author: HKUST-KnowComp
|
|
6
6
|
License-Expression: MIT
|
|
@@ -29,8 +29,8 @@ Dynamic: license-file
|
|
|
29
29
|
# DeepRefine-Skill
|
|
30
30
|
|
|
31
31
|
|
|
32
|
-
[](https://pypi.org/project/deeprefine-cli/0.1.
|
|
32
|
+
[](https://pypi.org/project/deeprefine-cli/0.1.5/)
|
|
33
|
+
[](https://pypi.org/project/deeprefine-cli/0.1.5/)
|
|
34
34
|
[](https://arxiv.org/pdf/2605.10488)
|
|
35
35
|
[](https://github.com/HKUST-KnowComp/DeepRefine)
|
|
36
36
|
|
|
@@ -38,7 +38,7 @@ Dynamic: license-file
|
|
|
38
38
|
|
|
39
39
|
Type `/deeprefine` in your AI coding assistant after you've built a **[graphify](https://github.com/safishamsi/graphify)** knowledge base — it patches `graphify-out/graph.json` from your session's query history to evolve your LLM-Wiki.
|
|
40
40
|
|
|
41
|
-
Works in **Cursor** (install the skill once with `deeprefine cursor install`).
|
|
41
|
+
Works in **Cursor** (install the skill once with `deeprefine cursor install`). In Cursor, `/deeprefine` runs in **agent-native mode** (no extra API key needed). The runtime CLI (`deeprefine refine`) is still available for vLLM/API execution.
|
|
42
42
|
|
|
43
43
|
```
|
|
44
44
|
/deeprefine
|
|
@@ -62,15 +62,14 @@ graphify-out/
|
|
|
62
62
|
```
|
|
63
63
|
|
|
64
64
|
> **Standalone repo.** Model code (`autorefiner`, `atlas_rag`) lives in a separate [DeepRefine](https://github.com/HKUST-KnowComp/DeepRefine) checkout.
|
|
65
|
-
> `pip install deeprefine-cli` ships the CLI and `SKILL.md`.
|
|
65
|
+
> `pip install deeprefine-cli` ships the CLI and `SKILL.md`. In Cursor, `/deeprefine` uses agent-native refinement; `deeprefine refine` uses DeepRefine runtime (vLLM/API) when you explicitly choose CLI execution.
|
|
66
66
|
|
|
67
67
|
---
|
|
68
68
|
|
|
69
|
-
##
|
|
69
|
+
## News
|
|
70
70
|
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
**Optional:** set custom OpenAI-compatible base URL and API key for LLM / embeddings.
|
|
71
|
+
- [2026/6/2] deeprefine-cli v0.1.5 has been released! Agent-native `/deeprefine` flow + clearer CLI/Agent split.
|
|
72
|
+
- [2026/6/2] deeprefine-cli v0.1.4 has been released! Customize your LLM api.
|
|
74
73
|
|
|
75
74
|
---
|
|
76
75
|
|
|
@@ -82,7 +81,7 @@ graphify-out/
|
|
|
82
81
|
| 2 | `pip install deeprefine-cli` |
|
|
83
82
|
| 3 | `deeprefine cursor install` in your KB project |
|
|
84
83
|
| 4 | (Optional) start local vLLM, or use your API provider |
|
|
85
|
-
| 5 | `
|
|
84
|
+
| 5 | Cursor chat: `/deeprefine` *(auto uses/adds query context)*; CLI mode: `history add` + `refine` |
|
|
86
85
|
|
|
87
86
|
```bash
|
|
88
87
|
# 1) DeepRefine (once)
|
|
@@ -111,11 +110,21 @@ export DEEPREFINE_EMBED_MODEL=your_embed_model
|
|
|
111
110
|
# export DEEPREFINE_API_KEY=your_shared_api_key
|
|
112
111
|
# optional model overrides:
|
|
113
112
|
|
|
114
|
-
#
|
|
113
|
+
# 5a) Refine in Cursor chat (agent-native, recommended)
|
|
114
|
+
# type in chat:
|
|
115
|
+
# /deeprefine
|
|
116
|
+
|
|
117
|
+
# 5b) Refine in terminal / CLI (manual flow)
|
|
115
118
|
deeprefine history add --query "your question"
|
|
116
119
|
deeprefine refine
|
|
117
120
|
```
|
|
118
121
|
|
|
122
|
+
In **Cursor chat** (agent):
|
|
123
|
+
|
|
124
|
+
```text
|
|
125
|
+
/deeprefine
|
|
126
|
+
```
|
|
127
|
+
|
|
119
128
|
---
|
|
120
129
|
|
|
121
130
|
## Pipeline
|
|
@@ -257,8 +266,8 @@ deeprefine cursor install
|
|
|
257
266
|
|:-:|--------|
|
|
258
267
|
| 1 | `graphify .` or `/graphify .` → `graphify-out/graph.json` |
|
|
259
268
|
| 2 | `graphify query "..."` |
|
|
260
|
-
| 3 | `
|
|
261
|
-
| 4 | `deeprefine
|
|
269
|
+
| 3 | Cursor chat: `/deeprefine` *(recommended; no manual `history add` needed)* |
|
|
270
|
+
| 4 | CLI alternative: `deeprefine history add --query "..."` → `deeprefine refine` |
|
|
262
271
|
| 5 | *(optional)* `graphify query "..."` to verify |
|
|
263
272
|
|
|
264
273
|
---
|
|
@@ -3,8 +3,8 @@
|
|
|
3
3
|
# DeepRefine-Skill
|
|
4
4
|
|
|
5
5
|
|
|
6
|
-
[](https://pypi.org/project/deeprefine-cli/0.1.
|
|
6
|
+
[](https://pypi.org/project/deeprefine-cli/0.1.5/)
|
|
7
|
+
[](https://pypi.org/project/deeprefine-cli/0.1.5/)
|
|
8
8
|
[](https://arxiv.org/pdf/2605.10488)
|
|
9
9
|
[](https://github.com/HKUST-KnowComp/DeepRefine)
|
|
10
10
|
|
|
@@ -12,7 +12,7 @@
|
|
|
12
12
|
|
|
13
13
|
Type `/deeprefine` in your AI coding assistant after you've built a **[graphify](https://github.com/safishamsi/graphify)** knowledge base — it patches `graphify-out/graph.json` from your session's query history to evolve your LLM-Wiki.
|
|
14
14
|
|
|
15
|
-
Works in **Cursor** (install the skill once with `deeprefine cursor install`).
|
|
15
|
+
Works in **Cursor** (install the skill once with `deeprefine cursor install`). In Cursor, `/deeprefine` runs in **agent-native mode** (no extra API key needed). The runtime CLI (`deeprefine refine`) is still available for vLLM/API execution.
|
|
16
16
|
|
|
17
17
|
```
|
|
18
18
|
/deeprefine
|
|
@@ -36,15 +36,14 @@ graphify-out/
|
|
|
36
36
|
```
|
|
37
37
|
|
|
38
38
|
> **Standalone repo.** Model code (`autorefiner`, `atlas_rag`) lives in a separate [DeepRefine](https://github.com/HKUST-KnowComp/DeepRefine) checkout.
|
|
39
|
-
> `pip install deeprefine-cli` ships the CLI and `SKILL.md`.
|
|
39
|
+
> `pip install deeprefine-cli` ships the CLI and `SKILL.md`. In Cursor, `/deeprefine` uses agent-native refinement; `deeprefine refine` uses DeepRefine runtime (vLLM/API) when you explicitly choose CLI execution.
|
|
40
40
|
|
|
41
41
|
---
|
|
42
42
|
|
|
43
|
-
##
|
|
43
|
+
## News
|
|
44
44
|
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
**Optional:** set custom OpenAI-compatible base URL and API key for LLM / embeddings.
|
|
45
|
+
- [2026/6/2] deeprefine-cli v0.1.5 has been released! Agent-native `/deeprefine` flow + clearer CLI/Agent split.
|
|
46
|
+
- [2026/6/2] deeprefine-cli v0.1.4 has been released! Customize your LLM api.
|
|
48
47
|
|
|
49
48
|
---
|
|
50
49
|
|
|
@@ -56,7 +55,7 @@ graphify-out/
|
|
|
56
55
|
| 2 | `pip install deeprefine-cli` |
|
|
57
56
|
| 3 | `deeprefine cursor install` in your KB project |
|
|
58
57
|
| 4 | (Optional) start local vLLM, or use your API provider |
|
|
59
|
-
| 5 | `
|
|
58
|
+
| 5 | Cursor chat: `/deeprefine` *(auto uses/adds query context)*; CLI mode: `history add` + `refine` |
|
|
60
59
|
|
|
61
60
|
```bash
|
|
62
61
|
# 1) DeepRefine (once)
|
|
@@ -85,11 +84,21 @@ export DEEPREFINE_EMBED_MODEL=your_embed_model
|
|
|
85
84
|
# export DEEPREFINE_API_KEY=your_shared_api_key
|
|
86
85
|
# optional model overrides:
|
|
87
86
|
|
|
88
|
-
#
|
|
87
|
+
# 5a) Refine in Cursor chat (agent-native, recommended)
|
|
88
|
+
# type in chat:
|
|
89
|
+
# /deeprefine
|
|
90
|
+
|
|
91
|
+
# 5b) Refine in terminal / CLI (manual flow)
|
|
89
92
|
deeprefine history add --query "your question"
|
|
90
93
|
deeprefine refine
|
|
91
94
|
```
|
|
92
95
|
|
|
96
|
+
In **Cursor chat** (agent):
|
|
97
|
+
|
|
98
|
+
```text
|
|
99
|
+
/deeprefine
|
|
100
|
+
```
|
|
101
|
+
|
|
93
102
|
---
|
|
94
103
|
|
|
95
104
|
## Pipeline
|
|
@@ -231,8 +240,8 @@ deeprefine cursor install
|
|
|
231
240
|
|:-:|--------|
|
|
232
241
|
| 1 | `graphify .` or `/graphify .` → `graphify-out/graph.json` |
|
|
233
242
|
| 2 | `graphify query "..."` |
|
|
234
|
-
| 3 | `
|
|
235
|
-
| 4 | `deeprefine
|
|
243
|
+
| 3 | Cursor chat: `/deeprefine` *(recommended; no manual `history add` needed)* |
|
|
244
|
+
| 4 | CLI alternative: `deeprefine history add --query "..."` → `deeprefine refine` |
|
|
236
245
|
| 5 | *(optional)* `graphify query "..."` to verify |
|
|
237
246
|
|
|
238
247
|
---
|
|
@@ -5,7 +5,7 @@ description: >-
|
|
|
5
5
|
Reafiner based on session query history. Use when the user runs /deeprefine,
|
|
6
6
|
asks to improve the graphify KB after Q&A, or wants to patch graph.json from
|
|
7
7
|
failed retrieval queries.
|
|
8
|
-
disable-model-invocation:
|
|
8
|
+
disable-model-invocation: false
|
|
9
9
|
---
|
|
10
10
|
|
|
11
11
|
# DeepRefine (graphify)
|
|
@@ -36,16 +36,24 @@ Inference defaults to your current API model setup (`OPENAI_API_KEY` or `DEEPREF
|
|
|
36
36
|
|
|
37
37
|
Optional: local vLLM from DeepRefine (embedding `8128`, refine model `8134`; see `scripts/vllm_serve/`).
|
|
38
38
|
|
|
39
|
-
## `/deeprefine`
|
|
39
|
+
## `/deeprefine` (agent-native)
|
|
40
40
|
|
|
41
41
|
From the **KB project root** (with `graphify-out/graph.json`):
|
|
42
42
|
|
|
43
43
|
```bash
|
|
44
44
|
deeprefine history add --query "..." # after graph Q&A
|
|
45
|
-
deeprefine
|
|
45
|
+
/deeprefine # run inside agent (no extra API key)
|
|
46
46
|
```
|
|
47
47
|
|
|
48
|
-
|
|
48
|
+
What the agent should do when `/deeprefine` is invoked:
|
|
49
|
+
|
|
50
|
+
1. Load pending queries from `graphify-out/.deeprefine/history.jsonl`.
|
|
51
|
+
2. Read `graphify-out/graph.json`.
|
|
52
|
+
3. Propose and apply minimal graph updates directly to `graph.json` for unresolved queries.
|
|
53
|
+
4. Write a timestamped log to `graphify-out/.deeprefine/refinement_results_*.jsonl`.
|
|
54
|
+
5. Mark processed history items as `refined: true`.
|
|
55
|
+
|
|
56
|
+
Use `deeprefine refine` CLI only when explicitly asked to run DeepRefine runtime (vLLM/API).
|
|
49
57
|
|
|
50
58
|
## Paths
|
|
51
59
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: deeprefine-cli
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.5
|
|
4
4
|
Summary: CLI and Cursor skill to refine graphify knowledge graphs with DeepRefine
|
|
5
5
|
Author: HKUST-KnowComp
|
|
6
6
|
License-Expression: MIT
|
|
@@ -29,8 +29,8 @@ Dynamic: license-file
|
|
|
29
29
|
# DeepRefine-Skill
|
|
30
30
|
|
|
31
31
|
|
|
32
|
-
[](https://pypi.org/project/deeprefine-cli/0.1.
|
|
32
|
+
[](https://pypi.org/project/deeprefine-cli/0.1.5/)
|
|
33
|
+
[](https://pypi.org/project/deeprefine-cli/0.1.5/)
|
|
34
34
|
[](https://arxiv.org/pdf/2605.10488)
|
|
35
35
|
[](https://github.com/HKUST-KnowComp/DeepRefine)
|
|
36
36
|
|
|
@@ -38,7 +38,7 @@ Dynamic: license-file
|
|
|
38
38
|
|
|
39
39
|
Type `/deeprefine` in your AI coding assistant after you've built a **[graphify](https://github.com/safishamsi/graphify)** knowledge base — it patches `graphify-out/graph.json` from your session's query history to evolve your LLM-Wiki.
|
|
40
40
|
|
|
41
|
-
Works in **Cursor** (install the skill once with `deeprefine cursor install`).
|
|
41
|
+
Works in **Cursor** (install the skill once with `deeprefine cursor install`). In Cursor, `/deeprefine` runs in **agent-native mode** (no extra API key needed). The runtime CLI (`deeprefine refine`) is still available for vLLM/API execution.
|
|
42
42
|
|
|
43
43
|
```
|
|
44
44
|
/deeprefine
|
|
@@ -62,15 +62,14 @@ graphify-out/
|
|
|
62
62
|
```
|
|
63
63
|
|
|
64
64
|
> **Standalone repo.** Model code (`autorefiner`, `atlas_rag`) lives in a separate [DeepRefine](https://github.com/HKUST-KnowComp/DeepRefine) checkout.
|
|
65
|
-
> `pip install deeprefine-cli` ships the CLI and `SKILL.md`.
|
|
65
|
+
> `pip install deeprefine-cli` ships the CLI and `SKILL.md`. In Cursor, `/deeprefine` uses agent-native refinement; `deeprefine refine` uses DeepRefine runtime (vLLM/API) when you explicitly choose CLI execution.
|
|
66
66
|
|
|
67
67
|
---
|
|
68
68
|
|
|
69
|
-
##
|
|
69
|
+
## News
|
|
70
70
|
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
**Optional:** set custom OpenAI-compatible base URL and API key for LLM / embeddings.
|
|
71
|
+
- [2026/6/2] deeprefine-cli v0.1.5 has been released! Agent-native `/deeprefine` flow + clearer CLI/Agent split.
|
|
72
|
+
- [2026/6/2] deeprefine-cli v0.1.4 has been released! Customize your LLM api.
|
|
74
73
|
|
|
75
74
|
---
|
|
76
75
|
|
|
@@ -82,7 +81,7 @@ graphify-out/
|
|
|
82
81
|
| 2 | `pip install deeprefine-cli` |
|
|
83
82
|
| 3 | `deeprefine cursor install` in your KB project |
|
|
84
83
|
| 4 | (Optional) start local vLLM, or use your API provider |
|
|
85
|
-
| 5 | `
|
|
84
|
+
| 5 | Cursor chat: `/deeprefine` *(auto uses/adds query context)*; CLI mode: `history add` + `refine` |
|
|
86
85
|
|
|
87
86
|
```bash
|
|
88
87
|
# 1) DeepRefine (once)
|
|
@@ -111,11 +110,21 @@ export DEEPREFINE_EMBED_MODEL=your_embed_model
|
|
|
111
110
|
# export DEEPREFINE_API_KEY=your_shared_api_key
|
|
112
111
|
# optional model overrides:
|
|
113
112
|
|
|
114
|
-
#
|
|
113
|
+
# 5a) Refine in Cursor chat (agent-native, recommended)
|
|
114
|
+
# type in chat:
|
|
115
|
+
# /deeprefine
|
|
116
|
+
|
|
117
|
+
# 5b) Refine in terminal / CLI (manual flow)
|
|
115
118
|
deeprefine history add --query "your question"
|
|
116
119
|
deeprefine refine
|
|
117
120
|
```
|
|
118
121
|
|
|
122
|
+
In **Cursor chat** (agent):
|
|
123
|
+
|
|
124
|
+
```text
|
|
125
|
+
/deeprefine
|
|
126
|
+
```
|
|
127
|
+
|
|
119
128
|
---
|
|
120
129
|
|
|
121
130
|
## Pipeline
|
|
@@ -257,8 +266,8 @@ deeprefine cursor install
|
|
|
257
266
|
|:-:|--------|
|
|
258
267
|
| 1 | `graphify .` or `/graphify .` → `graphify-out/graph.json` |
|
|
259
268
|
| 2 | `graphify query "..."` |
|
|
260
|
-
| 3 | `
|
|
261
|
-
| 4 | `deeprefine
|
|
269
|
+
| 3 | Cursor chat: `/deeprefine` *(recommended; no manual `history add` needed)* |
|
|
270
|
+
| 4 | CLI alternative: `deeprefine history add --query "..."` → `deeprefine refine` |
|
|
262
271
|
| 5 | *(optional)* `graphify query "..."` to verify |
|
|
263
272
|
|
|
264
273
|
---
|
|
@@ -5,7 +5,7 @@ description: >-
|
|
|
5
5
|
Reafiner based on session query history. Use when the user runs /deeprefine,
|
|
6
6
|
asks to improve the graphify KB after Q&A, or wants to patch graph.json from
|
|
7
7
|
failed retrieval queries.
|
|
8
|
-
disable-model-invocation:
|
|
8
|
+
disable-model-invocation: false
|
|
9
9
|
---
|
|
10
10
|
|
|
11
11
|
# DeepRefine (graphify)
|
|
@@ -36,16 +36,24 @@ Inference defaults to your current API model setup (`OPENAI_API_KEY` or `DEEPREF
|
|
|
36
36
|
|
|
37
37
|
Optional: local vLLM from DeepRefine (embedding `8128`, refine model `8134`; see `scripts/vllm_serve/`).
|
|
38
38
|
|
|
39
|
-
## `/deeprefine`
|
|
39
|
+
## `/deeprefine` (agent-native)
|
|
40
40
|
|
|
41
41
|
From the **KB project root** (with `graphify-out/graph.json`):
|
|
42
42
|
|
|
43
43
|
```bash
|
|
44
44
|
deeprefine history add --query "..." # after graph Q&A
|
|
45
|
-
deeprefine
|
|
45
|
+
/deeprefine # run inside agent (no extra API key)
|
|
46
46
|
```
|
|
47
47
|
|
|
48
|
-
|
|
48
|
+
What the agent should do when `/deeprefine` is invoked:
|
|
49
|
+
|
|
50
|
+
1. Load pending queries from `graphify-out/.deeprefine/history.jsonl`.
|
|
51
|
+
2. Read `graphify-out/graph.json`.
|
|
52
|
+
3. Propose and apply minimal graph updates directly to `graph.json` for unresolved queries.
|
|
53
|
+
4. Write a timestamped log to `graphify-out/.deeprefine/refinement_results_*.jsonl`.
|
|
54
|
+
5. Mark processed history items as `refined: true`.
|
|
55
|
+
|
|
56
|
+
Use `deeprefine refine` CLI only when explicitly asked to run DeepRefine runtime (vLLM/API).
|
|
49
57
|
|
|
50
58
|
## Paths
|
|
51
59
|
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|