Spaces:
Running
Running
Update requirements.txt
Browse files- requirements.txt +16 -16
requirements.txt
CHANGED
@@ -1,39 +1,39 @@
|
|
1 |
# ===============================
|
2 |
# π¦ Embedding + Vector Search
|
3 |
# ===============================
|
4 |
-
chromadb
|
5 |
-
sentence-transformers
|
6 |
-
torch
|
7 |
|
8 |
# ===============================
|
9 |
# π€ LLM-Based QA
|
10 |
# ===============================
|
11 |
-
transformers
|
12 |
-
accelerate
|
13 |
-
huggingface-hub
|
14 |
|
15 |
# ===============================
|
16 |
# π PDF Parsing
|
17 |
# ===============================
|
18 |
-
pymupdf
|
19 |
-
pdfminer.six
|
20 |
|
21 |
# ===============================
|
22 |
# πΌοΈ OCR + Image Handling
|
23 |
# ===============================
|
24 |
-
pytesseract
|
25 |
-
Pillow
|
26 |
|
27 |
# ===============================
|
28 |
# π UI Interface
|
29 |
# ===============================
|
30 |
-
gradio
|
31 |
-
requests
|
32 |
|
33 |
# ===============================
|
34 |
# π Utilities and Fixes
|
35 |
# ===============================
|
36 |
-
beautifulsoup4
|
37 |
-
pydantic
|
38 |
-
numpy
|
39 |
-
tqdm
|
|
|
1 |
# ===============================
|
2 |
# π¦ 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 |
# π€ 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 |
# π PDF Parsing
|
17 |
# ===============================
|
18 |
+
pymupdf # PyMuPDF for full-page text extraction
|
19 |
+
pdfminer.six # Optional: structured layout extraction
|
20 |
|
21 |
# ===============================
|
22 |
# πΌοΈ OCR + Image Handling
|
23 |
# ===============================
|
24 |
+
pytesseract # Requires separate install of Tesseract binary
|
25 |
+
Pillow
|
26 |
|
27 |
# ===============================
|
28 |
# π UI Interface
|
29 |
# ===============================
|
30 |
+
gradio # Gradio 4+ for modern UI
|
31 |
+
requests
|
32 |
|
33 |
# ===============================
|
34 |
# π 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)
|