Spaces:
Sleeping
Sleeping
Commit History
-
fix(reporting): keep reports in the stock's directory and sweep the scaffolding
Two corrections to where a report lands and what it leaves behind. The repository's top-level reports/ folder holds reference notes a person put there, not generated output. REPORTS_DIR and the --reports-dir flag are gone, and report_path() now resolves to output/<TICKER>/<TICKER>_report.pdf, which is where the API already looked for it. Nothing in the codebase writes to reports/ any more. Once the PDF compiles, the build's scaffolding is swept: the chart SVGs, the generated .typ, and any rendered page previews. All three are reproducible from the cached payloads, so the stock's directory holds the report rather than the sixteen files that produced it. --keep-build retains them, and a failed compile keeps them regardless -- the error names the retained source, which is the one moment they are worth having. The sweep is an allowlist of build byproducts, not "everything but the PDF". The same directory carries the ingestion layer's caches and the Drive upload record, which belong to o…ee5650f -
refactor!: hosted-model-only core, Drive report delivery, shared harnesses
Consolidates the platform onto one LLM path, one artifact layout and one verification harness, and removes the code that no longer has a caller. BREAKING: the Flask API is now search plus report delivery. The Self-RAG markdown report and DCF endpoints are gone with the services that produced them, and reports are addressed by their Google Drive link. core/ - llm_config.py talks to a single hosted OpenAI-compatible endpoint. The Ollama, Groq and Gemini branches and their environment variables are gone, along with create_client, create_content_part and read_file_content. A failure now raises LLMError: the previous fallback returned the prompt's own context, which a caller could not tell from real analysis. - config.py drops the hardcoded D:/Stock_Fundamental fallback and three unused dataclasses (FilePaths, WebsiteUrls, ApiEndpoints) that each carried a duplicate set of uppercase aliases. One artifact root per concern: REPORTS_DIR holds every finished PDF, OUTPUT_DIR hold…79cf149
-
refactor(retrieval): align section keys, remove hardcoded fallbacks, prune dead dependencies
Phase 2A - Retrieval core hygiene: - Align section keys between graph_pipeline and FinancialDataAgent so all eight report sections (company_overview, company_operations, expansion_plans, clients_market, financial_results, dupont_analysis, balance_sheet, strengths_weaknesses) resolve to live data tools, with a full-bundle fallback for unrecognized keys - Remove all hardcoded company-specific fallback literals from section context builders; report content is now derived entirely from live REST API metrics, WebSearch findings, and filing PDF retrieval for any ticker - Add GrowNXT Hosted Model API (OpenAI-compatible) as a provider in the LLM fallback chain - Add pypdf and pdfplumber to requirements; drop selenium and llama-index - Delete unused core/utils.py and legacy fetch scripts (fetch_financial_data.py, fetch_nifty50.py) - Ignore runtime data/ and reports/ directories Verified: a non-Wipro ticker (BIKAJI) generates a complete report with zero Wipro artifacts.4810792
-
refactor: modernize codebase to Pure Agentic RAG with live Vercel REST tools and Google Python Style Guide standards
1040058 -
Add DuPont Analysis ROE/ROCE decomposition and detailed concise bulletpoints
ShahStavand71d040
-
Restructured the directory structure and updated coding format as PEP8
ShahStavan7df950e