semantic-chunker-langchain 0.1.2__py3-none-any.whl → 0.1.3__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.
Files changed (5) hide show
  1. {semantic_chunker_langchain-0.1.2.dist-info → semantic_chunker_langchain-0.1.3.dist-info}/METADATA +5 -4
  2. {semantic_chunker_langchain-0.1.2.dist-info → semantic_chunker_langchain-0.1.3.dist-info}/RECORD +5 -5
  3. {semantic_chunker_langchain-0.1.2.dist-info → semantic_chunker_langchain-0.1.3.dist-info}/LICENSE +0 -0
  4. {semantic_chunker_langchain-0.1.2.dist-info → semantic_chunker_langchain-0.1.3.dist-info}/WHEEL +0 -0
  5. {semantic_chunker_langchain-0.1.2.dist-info → semantic_chunker_langchain-0.1.3.dist-info}/entry_points.txt +0 -0
{semantic_chunker_langchain-0.1.2.dist-info → semantic_chunker_langchain-0.1.3.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.3
2
2
  Name: semantic-chunker-langchain
3
- Version: 0.1.2
3
+ Version: 0.1.3
4
4
  Summary: Token-aware, LangChain-compatible semantic chunker with PDF and layout support
5
5
  License: MIT
6
6
  Author: Prajwal Shivaji Mandale
@@ -42,7 +42,7 @@ A **token-aware**, **LangChain-compatible** chunker that splits text (from PDF,
42
42
 
43
43
  ---
44
44
 
45
- ## 📦 Installation
45
+ ## 📆 Installation
46
46
 
47
47
  ```bash
48
48
  pip install semantic-chunker-langchain
@@ -62,6 +62,7 @@ semantic-chunker sample.pdf --txt chunks.txt --json chunks.json
62
62
 
63
63
  ### 🔸 From Code
64
64
 
65
+ ```python
65
66
  from semantic_chunker_langchain.chunker import SemanticChunker, SimpleSemanticChunker
66
67
  from semantic_chunker_langchain.extractors.pdf import extract_pdf
67
68
  from semantic_chunker_langchain.outputs.formatter import write_to_txt
@@ -79,7 +80,7 @@ write_to_txt(chunks, "output.txt")
79
80
  # Using SimpleSemanticChunker
80
81
  simple_chunker = SimpleSemanticChunker(model_name="gpt-3.5-turbo")
81
82
  simple_chunks = simple_chunker.split_documents(docs)
82
-
83
+ ```
83
84
 
84
85
  ### 🔸 Convert to Retriever
85
86
 
@@ -90,7 +91,7 @@ retriever = chunker.to_retriever(chunks, embedding=OpenAIEmbeddings())
90
91
 
91
92
  ---
92
93
 
93
- ## 🧪 Testing
94
+ ## 📊 Testing
94
95
 
95
96
  ```bash
96
97
  poetry run pytest tests/
{semantic_chunker_langchain-0.1.2.dist-info → semantic_chunker_langchain-0.1.3.dist-info}/RECORD RENAMED
@@ -3,8 +3,8 @@ semantic_chunker_langchain/chunker.py,sha256=6WdJMu1cI9hDPAM9ISJWpAhenrsOMNkiW5r
3
3
  semantic_chunker_langchain/extractors/pdf.py,sha256=8jRWBCMeIK3M_WgOyDqxxadEHQw678CzD5ryAJ0tvAA,356
4
4
  semantic_chunker_langchain/outputs/formatter.py,sha256=tYShwikgwIleV6Nz1ohmtGX6nQRVnY41NOkOT6v43Qk,964
5
5
  semantic_chunker_langchain/utils.py,sha256=E0Ajj2IBa6EFJJkGYZ8pyWUEKEAjiL9_Uof8KPnM8ew,288
6
- semantic_chunker_langchain-0.1.2.dist-info/entry_points.txt,sha256=Kve0GJQ5uzNSMBidDihM9sFuoUY90OeP5THfJWQLDVQ,45
7
- semantic_chunker_langchain-0.1.2.dist-info/LICENSE,sha256=vfqlCGc0OOjpze243uuSsBAAq1OFEoCLbmElHpljFWM,1111
8
- semantic_chunker_langchain-0.1.2.dist-info/METADATA,sha256=ozfUlZC1kMoImi9tA9xBZQkQ8TYZ52aHCHSDVuzIFlU,2906
9
- semantic_chunker_langchain-0.1.2.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
10
- semantic_chunker_langchain-0.1.2.dist-info/RECORD,,
6
+ semantic_chunker_langchain-0.1.3.dist-info/entry_points.txt,sha256=Kve0GJQ5uzNSMBidDihM9sFuoUY90OeP5THfJWQLDVQ,45
7
+ semantic_chunker_langchain-0.1.3.dist-info/LICENSE,sha256=vfqlCGc0OOjpze243uuSsBAAq1OFEoCLbmElHpljFWM,1111
8
+ semantic_chunker_langchain-0.1.3.dist-info/METADATA,sha256=ZJBOW8-1BHOTDPdlWBWFgwvlCIhvUJABEgBWEsyvGgU,2919
9
+ semantic_chunker_langchain-0.1.3.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
10
+ semantic_chunker_langchain-0.1.3.dist-info/RECORD,,