parsely-dip 0.0.0__py3-none-any.whl

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.
@@ -0,0 +1,3 @@
1
+ """PARSELY-DIP: Parsing And RegEx Syntactic Engine with Linguistic Yield - Deterministic Intent Parser"""
2
+
3
+ __version__ = "0.0.0"
File without changes
File without changes
File without changes
@@ -0,0 +1,80 @@
1
+ Metadata-Version: 2.4
2
+ Name: parsely-dip
3
+ Version: 0.0.0
4
+ Summary: PARSELY-DIP: Deterministic Intent Parser — RegEx and NLP pipeline for intent recognition
5
+ Author-email: George Butiri <george@iseestudios.com>
6
+ License-Expression: MIT
7
+ Project-URL: Homepage, https://github.com/gbutiri/parsely-dip
8
+ Keywords: nlp,intent,parser,deterministic,regex
9
+ Classifier: Development Status :: 1 - Planning
10
+ Classifier: Programming Language :: Python :: 3
11
+ Classifier: Topic :: Text Processing :: Linguistic
12
+ Requires-Python: >=3.9
13
+ Description-Content-Type: text/markdown
14
+
15
+ # PARSELY-DIP
16
+
17
+ **Parsing And RegEx Syntactic Engine with Linguistic Yield — Deterministic Intent Parser**
18
+
19
+ *Parsely dip for silicon chips.*
20
+
21
+ ## What It Does
22
+
23
+ PARSELY-DIP is a deterministic intent recognition engine. It processes natural language input through a cascading pipeline that resolves commands without an LLM whenever possible.
24
+
25
+ **Pipeline:** RegEx > Constituency + Dependency Parsing (Stanza) > LLM Fallback
26
+
27
+ Each layer only fires if the one above didn't match. The cheapest, fastest layer runs first. The LLM is the last resort, not the default.
28
+
29
+ ## Why It Exists
30
+
31
+ LLMs are expensive, slow, and unpredictable. When a user says "what time is it" or "move the card to done," there is zero ambiguity. A regex can handle it in microseconds. An LLM spends tokens guessing what you already know.
32
+
33
+ PARSELY-DIP intercepts deterministic commands before they reach the LLM, executes them directly, and returns the result. The LLM only gets involved when the input is genuinely ambiguous.
34
+
35
+ ## Architecture
36
+
37
+ ### Three-Tier Pipeline
38
+
39
+ 1. **RegEx Layer** — Pattern matching for known command structures. Fastest, cheapest, zero dependencies. Handles explicit commands and simple queries.
40
+
41
+ 2. **NLP Layer** — Stanza constituency and dependency parsing. Matches grammatical structure, not exact strings. Handles natural phrasing variations ("what's the time" vs "what time is it" vs "tell me the time").
42
+
43
+ 3. **LLM Fallback** — Only fires when neither deterministic layer can resolve the input. The input arrives with parsed metadata attached, so the LLM has structural context to work with.
44
+
45
+ ### Intent Libraries
46
+
47
+ Intent handlers are sideloadable — drop a folder into `intents/` to add new capabilities:
48
+
49
+ - Each library contains regex patterns, NLP patterns, and handler functions
50
+ - Libraries are self-registering via decorators
51
+ - Base examples: time telling, weather, scrum card operations
52
+
53
+ ### Integration
54
+
55
+ Designed to run as a Claude Code `UserPromptSubmit` hook. The hook intercepts the user's message, runs it through the pipeline, and either:
56
+ - **Handles it** — executes the command, returns the result
57
+ - **Passes through** — no match, the LLM processes it normally
58
+
59
+ ## Pattern Convention
60
+
61
+ RegEx patterns use leading `\s+` before words, not trailing:
62
+
63
+ ```
64
+ CORRECT: (what('s|\s+is)\s+the\s+time|what\s+time\s+is\s+it)
65
+ WRONG: (what('s|is\s+)the\s+time\s+|what\s+time\s+is\s+it\s+)
66
+ ```
67
+
68
+ The space belongs to the approach of the next word, not trailing from the previous.
69
+
70
+ ## Status
71
+
72
+ v0.0.0 — Package name placeholder. Development starting.
73
+
74
+ ## License
75
+
76
+ Source-available. Personal and development use permitted.
77
+
78
+ ## Author
79
+
80
+ George Butiri — [george@iseestudios.com](mailto:george@iseestudios.com)
@@ -0,0 +1,8 @@
1
+ parsely_dip/__init__.py,sha256=JmaEm79MFdZxCsY0zjPPW-TrpOdzlqAaNlGSH273fZY,129
2
+ parsely_dip/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
3
+ parsely_dip/engine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
4
+ parsely_dip/intents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
5
+ parsely_dip-0.0.0.dist-info/METADATA,sha256=nU0e8zhSOxn9uklhOhrjujzxXH9Ggf6Xt7yifOs3B-M,3345
6
+ parsely_dip-0.0.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
7
+ parsely_dip-0.0.0.dist-info/top_level.txt,sha256=6emsWMLboCA1KT61FjvrY_rlXhDt4rNEkDqjHiZkjaI,12
8
+ parsely_dip-0.0.0.dist-info/RECORD,,
@@ -0,0 +1,5 @@
1
+ Wheel-Version: 1.0
2
+ Generator: setuptools (82.0.1)
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any
5
+
@@ -0,0 +1 @@
1
+ parsely_dip