damoojeje commited on
Commit
44d1669
Β·
verified Β·
1 Parent(s): f43e8a0

Update requirements.txt

Browse files
Files changed (1) hide show
  1. requirements.txt +16 -16
requirements.txt CHANGED
@@ -1,39 +1,39 @@
1
  # ===============================
2
  # πŸ“¦ Embedding + Vector Search
3
  # ===============================
4
- chromadb==0.4.24
5
- sentence-transformers==2.4.0 # Compatible with huggingface-hub 0.30.1
6
- torch>=1.13.1, <2.0.0 # Stable with sentence-transformers
7
 
8
  # ===============================
9
  # πŸ€– LLM-Based QA
10
  # ===============================
11
- transformers==4.37.2 # Works well with huggingface-hub 0.30.1
12
- accelerate>=0.26.1
13
- huggingface-hub==0.30.1 # Compatible with transformers 4.37.2
14
 
15
  # ===============================
16
  # πŸ“„ PDF Parsing
17
  # ===============================
18
- pymupdf>=1.25.5 # PyMuPDF for full-page text extraction
19
- pdfminer.six>=20221105 # Optional: structured layout extraction
20
 
21
  # ===============================
22
  # πŸ–ΌοΈ OCR + Image Handling
23
  # ===============================
24
- pytesseract>=0.3.10 # Requires separate install of Tesseract binary
25
- Pillow>=9.4.0
26
 
27
  # ===============================
28
  # 🌐 UI Interface
29
  # ===============================
30
- gradio>=4.29.0 # Gradio 4+ for modern UI
31
- requests>=2.31.0
32
 
33
  # ===============================
34
  # πŸ›  Utilities and Fixes
35
  # ===============================
36
- beautifulsoup4>=4.12.2 # Parsing for HTML-in-PDFs (e.g., diagrams/tables)
37
- pydantic<2.0.0 # Chromadb is not yet compatible with pydantic 2.x
38
- numpy==1.26.4 # Ensures compatibility with chromadb and transformers
39
- tqdm>=4.66.0 # Progress bar (used in embedding scripts)
 
1
  # ===============================
2
  # πŸ“¦ Embedding + Vector Search
3
  # ===============================
4
+ chromadb
5
+ sentence-transformers # Compatible with huggingface-hub 0.30.1
6
+ torch # Stable with sentence-transformers
7
 
8
  # ===============================
9
  # πŸ€– LLM-Based QA
10
  # ===============================
11
+ transformers # Works well with huggingface-hub 0.30.1
12
+ accelerate
13
+ huggingface-hub # Compatible with transformers 4.37.2
14
 
15
  # ===============================
16
  # πŸ“„ PDF Parsing
17
  # ===============================
18
+ pymupdf # PyMuPDF for full-page text extraction
19
+ pdfminer.six # Optional: structured layout extraction
20
 
21
  # ===============================
22
  # πŸ–ΌοΈ OCR + Image Handling
23
  # ===============================
24
+ pytesseract # Requires separate install of Tesseract binary
25
+ Pillow
26
 
27
  # ===============================
28
  # 🌐 UI Interface
29
  # ===============================
30
+ gradio # Gradio 4+ for modern UI
31
+ requests
32
 
33
  # ===============================
34
  # πŸ›  Utilities and Fixes
35
  # ===============================
36
+ beautifulsoup4 # Parsing for HTML-in-PDFs (e.g., diagrams/tables)
37
+ pydantic # Chromadb is not yet compatible with pydantic 2.x
38
+ numpy # Ensures compatibility with chromadb and transformers
39
+ tqdm # Progress bar (used in embedding scripts)