Resolve DoclingParser exports, fix Windows progress encoding, and update finance cookbook #138

This commit is contained in:
KaifAhmad1
2026-01-05 20:04:59 +05:30
parent ef2c3dc841
commit 4e0c3bc361
3 changed files with 16 additions and 8 deletions
@@ -6,19 +6,28 @@
"source": [
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Hawksight-AI/semantica/blob/main/cookbook/use_cases/finance/03_Earnings_Call_Analysis.ipynb)\n",
"\n",
"# Earnings Call Transcript Analysis with Docling and Semantica\n",
"# Earnings Call Analysis with Docling and Semantica: MDA Space Q3 2025\n",
"\n",
"## 📄 Earnings Call Transcript PDF\n",
"## Data Sources\n",
"\n",
"**Example:** Download a single earnings call transcript PDF from [SEC EDGAR](https://www.sec.gov/edgar/searchedgar/companysearch.html) or company investor relations pages. Use one PDF file for this analysis.\n",
"This analysis dual-tracks two critical documents from **MDA Space Ltd.** for the third quarter of 2025 to provide a holistic view of the company's performance and strategy:\n",
"1. **Press Release:** A structured summary of financial results, strategic milestones, and executive commentary.\n",
"2. **Earnings Transcript:** A detailed record of the management presentation and the subsequent Q&A session with analysts, providing deeper qualitative context.\n",
"\n",
"### Q3 2025 Strategic Highlights\n",
"* **Robust Backlog:** The company maintained a significant backlog at quarter-end, providing strong revenue visibility and supporting long-term growth objectives.\n",
"* **Strong Revenue Growth:** Substantial year-over-year revenue expansion driven by successful execution across major programs and satellite system deliveries.\n",
"* **Profitability & Margins:** Strong operational performance led to a significant increase in Adjusted EBITDA and healthy overall margin expansion.\n",
"* **Earnings Performance:** Noteworthy growth in adjusted net income and earnings per share, reflecting scaled operations and improved bottom-line efficiency.\n",
"* **Cash Flow & Capital Structure:** Positive operating cash flow and a healthy balance sheet with a very low leverage ratio, positioning the company well for future investment.\n",
"\n",
"---\n",
"\n",
"## Overview\n",
"\n",
"Extract insights from earnings call transcripts by building a knowledge graph with entity extraction, relationship mapping, and GraphRAG-powered Q&A.\n",
"This notebook demonstrates how to extract deep insights from unstructured financial documents. By combining **Docling** for high-fidelity parsing with **Semantica** for knowledge engineering, we build a structured semantic layer that enables complex analysis and advanced GraphRAG capabilities.\n",
"\n",
"**Workflow:** `PDF → Parse → Extract Entities/Relations → Build KG → GraphRAG → Answers`\n"
"**Workflow:** `Dual PDF Input → Docling Parsing → Entity & Relation Extraction → Knowledge Graph Construction → GraphRAG → Strategic Q&A`"
]
},
{
+1 -2
View File
@@ -170,8 +170,7 @@ from .pptx_parser import PPTXData, PPTXParser, SlideContent
# Try to import DoclingParser (optional dependency)
try:
from .docling_parser import DoclingParser, DoclingMetadata
DOCLING_AVAILABLE = True
from .docling_parser import DoclingParser, DoclingMetadata, DOCLING_AVAILABLE
except (ImportError, OSError):
DOCLING_AVAILABLE = False
DoclingParser = None
+1 -1
View File
@@ -357,7 +357,7 @@ class ConsoleProgressDisplay(ProgressDisplay):
line = " ".join(parts)
self.current_lines[key] = line
sys.stdout.write(line)
self._safe_write(line)
def show_summary(self, items: List[ProgressItem]) -> None:
"""Show final summary."""