deepresearch-flow 0.2.1__tar.gz → 0.4.0__tar.gz

{deepresearch_flow-0.2.1 → deepresearch_flow-0.4.0}/MANIFEST.in

@@ -5,3 +5,5 @@ recursive-include python/deepresearch_flow/paper/templates *.j2
 recursive-include python/deepresearch_flow/paper/prompt_templates *.j2
 recursive-include python/deepresearch_flow/paper/examples *.toml
 recursive-include python/deepresearch_flow/paper/web/pdfjs *
+recursive-include python/deepresearch_flow/paper/web/templates *
+recursive-include python/deepresearch_flow/paper/web/static *

deepresearch_flow-0.4.0/PKG-INFO

@@ -0,0 +1,327 @@
+Metadata-Version: 2.4
+Name: deepresearch-flow
+Version: 0.4.0
+Summary: Workflow tools for paper extraction, review, and research automation.
+Author-email: DengQi <dengqi935@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2025 DengQi
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://github.com/nerdneilsfield/ai-deepresearch-flow
+Project-URL: Repository, https://github.com/nerdneilsfield/ai-deepresearch-flow
+Project-URL: Issues, https://github.com/nerdneilsfield/ai-deepresearch-flow/issues
+Keywords: research,papers,pdf,ocr,llm,workflow
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: anthropic>=0.28.0
+Requires-Dist: click>=8.1.7
+Requires-Dist: coloredlogs>=15.0.1
+Requires-Dist: dashscope>=1.20.0
+Requires-Dist: google-auth>=2.0.0
+Requires-Dist: google-genai>=0.5.0
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: jinja2>=3.1.3
+Requires-Dist: json-repair>=0.31.0
+Requires-Dist: jsonschema>=4.21.1
+Requires-Dist: markdown-it-py>=3.0.0
+Requires-Dist: mdit-py-plugins>=0.4.0
+Requires-Dist: pypdf>=3.0.0
+Requires-Dist: pybtex>=0.24.0
+Requires-Dist: rich>=13.7.1
+Requires-Dist: rumdl>=0.0.214
+Requires-Dist: starlette>=0.37.2
+Requires-Dist: tqdm>=4.66.4
+Requires-Dist: uvicorn>=0.27.1
+Dynamic: license-file
+
+<p align="center">
+  <img src=".github/assets/logo.png" width="140" alt="ai-deepresearch-flow logo" />
+</p>
+
+<h3 align="center">ai-deepresearch-flow</h3>
+
+<p align="center">
+  <em>From documents to deep research insight — automatically.</em>
+</p>
+
+<p align="center">
+  <a href="README.md">English</a> | <a href="README_ZH.md">中文</a>
+</p>
+
+<p align="center">
+  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/actions">
+    <img src="https://img.shields.io/github/actions/workflow/status/nerdneilsfield/ai-deepresearch-flow/push-to-pypi.yml?style=flat-square" />
+  </a>
+  <a href="https://pypi.org/project/deepresearch-flow/">
+    <img src="https://img.shields.io/pypi/v/deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://pypi.org/project/deepresearch-flow/">
+    <img src="https://img.shields.io/pypi/pyversions/deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://hub.docker.com/r/nerdneils/deepresearch-flow">
+    <img src="https://img.shields.io/docker/v/nerdneils/deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://ghcr.io/nerdneilsfield/deepresearch-flow">
+    <img src="https://img.shields.io/badge/ghcr.io-nerdneilsfield%2Fdeepresearch-flow-0f172a?style=flat-square" />
+  </a>
+  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/blob/main/LICENSE">
+    <img src="https://img.shields.io/github/license/nerdneilsfield/ai-deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/stargazers">
+    <img src="https://img.shields.io/github/stars/nerdneilsfield/ai-deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://pypi.org/project/deepresearch-flow">
+  <img alt="PyPI - Version" src="https://img.shields.io/pypi/v/deepresearch-flow">
+  </a>
+  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/issues">
+    <img src="https://img.shields.io/github/issues/nerdneilsfield/ai-deepresearch-flow?style=flat-square" />
+  </a>
+</p>
+
+---
+
+## The Core Pain Points
+
+- **OCR Chaos**: Raw markdown from OCR tools is often broken -- tables drift, formulas break, and references are non-clickable.
+- **Translation Nightmares**: Translating technical papers often destroys code blocks, LaTeX formulas, and table structures.
+- **Information Overload**: Extracting structured insights (authors, venues, summaries) from hundreds of PDFs manually is impossible.
+- **Context Switching**: Managing PDFs, summaries, and translations in different windows kills focus.
+
+## The Solution
+
+DeepResearch Flow provides a unified pipeline to **Repair**, **Translate**, **Extract**, and **Serve** your research library.
+
+## Key Features
+
+- **Smart Extraction**: Turn unstructured Markdown into schema-enforced JSON (summaries, metadata, Q&A) using LLMs (OpenAI, Claude, Gemini, etc.).
+- **Precision Translation**: Translate OCR Markdown to Chinese/Japanese (`.zh.md`, `.ja.md`) while **freezing** formulas, code, tables, and references. No more broken layout.
+- **Local Knowledge DB**: A high-performance local Web UI to browse papers with **Split View** (Source vs. Translated vs. Summary), full-text search, and multi-dimensional filtering.
+- **Coverage Compare**: Compare JSON/PDF/Markdown/Translated datasets to find missing artifacts and export CSV reports.
+- **OCR Post-Processing**: Automatically fix broken references (`[1]` -> `[^1]`), merge split paragraphs, and standardize layouts.
+
+---
+
+## Quick Start
+
+### 1) Installation
+
+```bash
+# Recommended: using uv for speed
+uv pip install deepresearch-flow
+
+# Or standard pip
+pip install deepresearch-flow
+```
+
+### 2) Configuration
+
+Set up your LLM providers. We support OpenAI, Claude, Gemini, Ollama, and more.
+
+```bash
+cp config.example.toml config.toml
+# Edit config.toml to add your API keys (e.g., env:OPENAI_API_KEY)
+```
+
+### 3) The "Zero to Hero" Workflow
+
+#### Step 1: Extract Insights
+
+Scan a folder of markdown files and extract structured summaries.
+
+```bash
+uv run deepresearch-flow paper extract \
+  --input ./docs \
+  --model openai/gpt-4o-mini \
+  --prompt-template deep_read
+```
+
+#### Step 2: Translate Safely
+
+Translate papers to Chinese, protecting LaTeX and tables.
+
+```bash
+uv run deepresearch-flow translator translate \
+  --input ./docs \
+  --target-lang zh \
+  --model openai/gpt-4o-mini \
+  --fix-level moderate
+```
+
+#### Step 3: Serve Your Database
+
+Launch a local UI to read and manage your papers.
+
+```bash
+uv run deepresearch-flow paper db serve \
+  --input paper_infos.json \
+  --md-root ./docs \
+  --md-translated-root ./docs \
+  --host 127.0.0.1
+```
+
+---
+
+## Comprehensive Guide
+
+<details>
+<summary><strong>1. Translator: OCR-Safe Translation</strong></summary>
+
+The translator module is built for scientific documents. It uses a node-based architecture to ensure stability.
+
+- Structure Protection: automatically detects and "freezes" code blocks, LaTeX (`$$...$$`), HTML tables, and images before sending text to the LLM.
+- OCR Repair: use `--fix-level` to merge broken paragraphs and convert text references (`[1]`) to clickable Markdown footnotes (`[^1]`).
+- Context-Aware: supports retries for failed chunks and falls back gracefully.
+
+```bash
+# Translate with structure protection and OCR repairs
+uv run deepresearch-flow translator translate \
+  --input ./paper.md \
+  --target-lang ja \
+  --fix-level aggressive \
+  --model claude/claude-3-5-sonnet-20240620
+```
+
+</details>
+
+<details>
+<summary><strong>2. Paper Extract: Structured Knowledge</strong></summary>
+
+Turn loose markdown files into a queryable database.
+
+- Templates: built-in prompts like `simple`, `eight_questions`, and `deep_read` guide the LLM to extract specific insights.
+- Async and throttled: precise control over concurrency (`--max-concurrency`) and rate limits (`--sleep-every`).
+- Incremental: skips already processed files; resumes from where you left off.
+
+```bash
+uv run deepresearch-flow paper extract \
+  --input ./library \
+  --output paper_data.json \
+  --template-dir ./my-custom-prompts \
+  --max-concurrency 10
+```
+
+</details>
+
+<details>
+<summary><strong>3. Database and UI: Your Personal ArXiv</strong></summary>
+
+The db serve command creates a local research station.
+
+- Split View: read the original PDF/Markdown on the left and the Summary/Translation on the right.
+- Full Text Search: search by title, author, year, or content tags (`tag:fpga year:2023..2024`).
+- Stats: visualize publication trends and keyword frequencies.
+- PDF Viewer: built-in PDF.js viewer prevents cross-origin issues with local files.
+
+```bash
+uv run deepresearch-flow paper db serve \
+  --input paper_infos.json \
+  --pdf-root ./pdfs \
+  --cache-dir .cache/db
+```
+
+</details>
+
+<details>
+<summary><strong>4. Paper DB Compare: Coverage Audit</strong></summary>
+
+Compare two datasets (A/B) to find missing PDFs, markdowns, translations, or JSON items, with match metadata.
+
+```bash
+uv run deepresearch-flow paper db compare \
+  --input-a ./a.json \
+  --md-root-b ./md_root \
+  --output-csv ./compare.csv
+
+# Compare translated markdowns by language
+uv run deepresearch-flow paper db compare \
+  --md-translated-root-a ./translated_a \
+  --md-translated-root-b ./translated_b \
+  --lang zh
+```
+
+</details>
+
+<details>
+<summary><strong>5. Recognize: OCR Post-Processing</strong></summary>
+
+Tools to clean up raw outputs from OCR engines like MinerU.
+
+- Embed Images: convert local image links to Base64 for a portable single-file Markdown.
+- Unpack Images: extract Base64 images back to files.
+- Organize: flatten nested OCR output directories.
+- Fix: apply OCR fixes and rumdl formatting during organize, or as a standalone step.
+
+```bash
+uv run deepresearch-flow recognize md embed --input ./raw_ocr --output ./clean_md
+```
+
+```bash
+# Organize MinerU output and apply OCR fixes
+uv run deepresearch-flow recognize organize \
+  --input ./mineru_outputs \
+  --output-simple ./ocr_md \
+  --fix
+
+# Fix and format existing markdown outputs
+uv run deepresearch-flow recognize fix \
+  --input ./ocr_md \
+  --output ./ocr_md_fixed
+
+# Fix in place
+uv run deepresearch-flow recognize fix \
+  --input ./ocr_md \
+  --in-place
+```
+
+</details>
+
+---
+
+## Docker Support
+
+Don't want to manage Python environments?
+
+```bash
+docker run --rm -v $(pwd):/app -it ghcr.io/nerdneilsfield/deepresearch-flow --help
+```
+
+## Configuration
+
+The config.toml is your control center. It supports:
+
+- Multiple Providers: mix and match OpenAI, DeepSeek (DashScope), Gemini, Claude, and Ollama.
+- Model Routing: explicit routing to specific models (`--model provider/model_name`).
+- Environment Variables: keep secrets safe using `env:VAR_NAME` syntax.
+
+See `config.example.toml` for a full reference.
+
+---
+
+<p align="center">
+  Built with love for the Open Science community.
+</p>

deepresearch_flow-0.4.0/README.md

@@ -0,0 +1,266 @@
+<p align="center">
+  <img src=".github/assets/logo.png" width="140" alt="ai-deepresearch-flow logo" />
+</p>
+
+<h3 align="center">ai-deepresearch-flow</h3>
+
+<p align="center">
+  <em>From documents to deep research insight — automatically.</em>
+</p>
+
+<p align="center">
+  <a href="README.md">English</a> | <a href="README_ZH.md">中文</a>
+</p>
+
+<p align="center">
+  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/actions">
+    <img src="https://img.shields.io/github/actions/workflow/status/nerdneilsfield/ai-deepresearch-flow/push-to-pypi.yml?style=flat-square" />
+  </a>
+  <a href="https://pypi.org/project/deepresearch-flow/">
+    <img src="https://img.shields.io/pypi/v/deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://pypi.org/project/deepresearch-flow/">
+    <img src="https://img.shields.io/pypi/pyversions/deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://hub.docker.com/r/nerdneils/deepresearch-flow">
+    <img src="https://img.shields.io/docker/v/nerdneils/deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://ghcr.io/nerdneilsfield/deepresearch-flow">
+    <img src="https://img.shields.io/badge/ghcr.io-nerdneilsfield%2Fdeepresearch-flow-0f172a?style=flat-square" />
+  </a>
+  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/blob/main/LICENSE">
+    <img src="https://img.shields.io/github/license/nerdneilsfield/ai-deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/stargazers">
+    <img src="https://img.shields.io/github/stars/nerdneilsfield/ai-deepresearch-flow?style=flat-square" />
+  </a>
+  <a href="https://pypi.org/project/deepresearch-flow">
+  <img alt="PyPI - Version" src="https://img.shields.io/pypi/v/deepresearch-flow">
+  </a>
+  <a href="https://github.com/nerdneilsfield/ai-deepresearch-flow/issues">
+    <img src="https://img.shields.io/github/issues/nerdneilsfield/ai-deepresearch-flow?style=flat-square" />
+  </a>
+</p>
+
+---
+
+## The Core Pain Points
+
+- **OCR Chaos**: Raw markdown from OCR tools is often broken -- tables drift, formulas break, and references are non-clickable.
+- **Translation Nightmares**: Translating technical papers often destroys code blocks, LaTeX formulas, and table structures.
+- **Information Overload**: Extracting structured insights (authors, venues, summaries) from hundreds of PDFs manually is impossible.
+- **Context Switching**: Managing PDFs, summaries, and translations in different windows kills focus.
+
+## The Solution
+
+DeepResearch Flow provides a unified pipeline to **Repair**, **Translate**, **Extract**, and **Serve** your research library.
+
+## Key Features
+
+- **Smart Extraction**: Turn unstructured Markdown into schema-enforced JSON (summaries, metadata, Q&A) using LLMs (OpenAI, Claude, Gemini, etc.).
+- **Precision Translation**: Translate OCR Markdown to Chinese/Japanese (`.zh.md`, `.ja.md`) while **freezing** formulas, code, tables, and references. No more broken layout.
+- **Local Knowledge DB**: A high-performance local Web UI to browse papers with **Split View** (Source vs. Translated vs. Summary), full-text search, and multi-dimensional filtering.
+- **Coverage Compare**: Compare JSON/PDF/Markdown/Translated datasets to find missing artifacts and export CSV reports.
+- **OCR Post-Processing**: Automatically fix broken references (`[1]` -> `[^1]`), merge split paragraphs, and standardize layouts.
+
+---
+
+## Quick Start
+
+### 1) Installation
+
+```bash
+# Recommended: using uv for speed
+uv pip install deepresearch-flow
+
+# Or standard pip
+pip install deepresearch-flow
+```
+
+### 2) Configuration
+
+Set up your LLM providers. We support OpenAI, Claude, Gemini, Ollama, and more.
+
+```bash
+cp config.example.toml config.toml
+# Edit config.toml to add your API keys (e.g., env:OPENAI_API_KEY)
+```
+
+### 3) The "Zero to Hero" Workflow
+
+#### Step 1: Extract Insights
+
+Scan a folder of markdown files and extract structured summaries.
+
+```bash
+uv run deepresearch-flow paper extract \
+  --input ./docs \
+  --model openai/gpt-4o-mini \
+  --prompt-template deep_read
+```
+
+#### Step 2: Translate Safely
+
+Translate papers to Chinese, protecting LaTeX and tables.
+
+```bash
+uv run deepresearch-flow translator translate \
+  --input ./docs \
+  --target-lang zh \
+  --model openai/gpt-4o-mini \
+  --fix-level moderate
+```
+
+#### Step 3: Serve Your Database
+
+Launch a local UI to read and manage your papers.
+
+```bash
+uv run deepresearch-flow paper db serve \
+  --input paper_infos.json \
+  --md-root ./docs \
+  --md-translated-root ./docs \
+  --host 127.0.0.1
+```
+
+---
+
+## Comprehensive Guide
+
+<details>
+<summary><strong>1. Translator: OCR-Safe Translation</strong></summary>
+
+The translator module is built for scientific documents. It uses a node-based architecture to ensure stability.
+
+- Structure Protection: automatically detects and "freezes" code blocks, LaTeX (`$$...$$`), HTML tables, and images before sending text to the LLM.
+- OCR Repair: use `--fix-level` to merge broken paragraphs and convert text references (`[1]`) to clickable Markdown footnotes (`[^1]`).
+- Context-Aware: supports retries for failed chunks and falls back gracefully.
+
+```bash
+# Translate with structure protection and OCR repairs
+uv run deepresearch-flow translator translate \
+  --input ./paper.md \
+  --target-lang ja \
+  --fix-level aggressive \
+  --model claude/claude-3-5-sonnet-20240620
+```
+
+</details>
+
+<details>
+<summary><strong>2. Paper Extract: Structured Knowledge</strong></summary>
+
+Turn loose markdown files into a queryable database.
+
+- Templates: built-in prompts like `simple`, `eight_questions`, and `deep_read` guide the LLM to extract specific insights.
+- Async and throttled: precise control over concurrency (`--max-concurrency`) and rate limits (`--sleep-every`).
+- Incremental: skips already processed files; resumes from where you left off.
+
+```bash
+uv run deepresearch-flow paper extract \
+  --input ./library \
+  --output paper_data.json \
+  --template-dir ./my-custom-prompts \
+  --max-concurrency 10
+```
+
+</details>
+
+<details>
+<summary><strong>3. Database and UI: Your Personal ArXiv</strong></summary>
+
+The db serve command creates a local research station.
+
+- Split View: read the original PDF/Markdown on the left and the Summary/Translation on the right.
+- Full Text Search: search by title, author, year, or content tags (`tag:fpga year:2023..2024`).
+- Stats: visualize publication trends and keyword frequencies.
+- PDF Viewer: built-in PDF.js viewer prevents cross-origin issues with local files.
+
+```bash
+uv run deepresearch-flow paper db serve \
+  --input paper_infos.json \
+  --pdf-root ./pdfs \
+  --cache-dir .cache/db
+```
+
+</details>
+
+<details>
+<summary><strong>4. Paper DB Compare: Coverage Audit</strong></summary>
+
+Compare two datasets (A/B) to find missing PDFs, markdowns, translations, or JSON items, with match metadata.
+
+```bash
+uv run deepresearch-flow paper db compare \
+  --input-a ./a.json \
+  --md-root-b ./md_root \
+  --output-csv ./compare.csv
+
+# Compare translated markdowns by language
+uv run deepresearch-flow paper db compare \
+  --md-translated-root-a ./translated_a \
+  --md-translated-root-b ./translated_b \
+  --lang zh
+```
+
+</details>
+
+<details>
+<summary><strong>5. Recognize: OCR Post-Processing</strong></summary>
+
+Tools to clean up raw outputs from OCR engines like MinerU.
+
+- Embed Images: convert local image links to Base64 for a portable single-file Markdown.
+- Unpack Images: extract Base64 images back to files.
+- Organize: flatten nested OCR output directories.
+- Fix: apply OCR fixes and rumdl formatting during organize, or as a standalone step.
+
+```bash
+uv run deepresearch-flow recognize md embed --input ./raw_ocr --output ./clean_md
+```
+
+```bash
+# Organize MinerU output and apply OCR fixes
+uv run deepresearch-flow recognize organize \
+  --input ./mineru_outputs \
+  --output-simple ./ocr_md \
+  --fix
+
+# Fix and format existing markdown outputs
+uv run deepresearch-flow recognize fix \
+  --input ./ocr_md \
+  --output ./ocr_md_fixed
+
+# Fix in place
+uv run deepresearch-flow recognize fix \
+  --input ./ocr_md \
+  --in-place
+```
+
+</details>
+
+---
+
+## Docker Support
+
+Don't want to manage Python environments?
+
+```bash
+docker run --rm -v $(pwd):/app -it ghcr.io/nerdneilsfield/deepresearch-flow --help
+```
+
+## Configuration
+
+The config.toml is your control center. It supports:
+
+- Multiple Providers: mix and match OpenAI, DeepSeek (DashScope), Gemini, Claude, and Ollama.
+- Model Routing: explicit routing to specific models (`--model provider/model_name`).
+- Environment Variables: keep secrets safe using `env:VAR_NAME` syntax.
+
+See `config.example.toml` for a full reference.
+
+---
+
+<p align="center">
+  Built with love for the Open Science community.
+</p>

{deepresearch_flow-0.2.1 → deepresearch_flow-0.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "deepresearch-flow"
-version = "0.2.1"
+version = "0.4.0"
 description = "Workflow tools for paper extraction, review, and research automation."
 readme = { file = "README.md", content-type = "text/markdown" }
 license = { file = "LICENSE" }
@@ -18,9 +18,11 @@ dependencies = [
     "json-repair>=0.31.0",
     "jsonschema>=4.21.1",
     "markdown-it-py>=3.0.0",
+    "mdit-py-plugins>=0.4.0",
     "pypdf>=3.0.0",
     "pybtex>=0.24.0",
     "rich>=13.7.1",
+    "rumdl>=0.0.214",
     "starlette>=0.37.2",
     "tqdm>=4.66.4",
     "uvicorn>=0.27.1",
@@ -57,4 +59,4 @@ include-package-data = true
 "deepresearch_flow.paper.templates" = ["*.j2"]
 "deepresearch_flow.paper.prompt_templates" = ["*.j2"]
 "deepresearch_flow.paper.examples" = ["*.toml"]
-"deepresearch_flow.paper.web" = ["pdfjs/**/*"]
+"deepresearch_flow.paper.web" = ["pdfjs/**/*", "templates/**/*", "static/**/*"]

{deepresearch_flow-0.2.1 → deepresearch_flow-0.4.0}/python/deepresearch_flow/cli.py

@@ -4,6 +4,7 @@ import click
 
 from deepresearch_flow.paper.cli import paper
 from deepresearch_flow.recognize.cli import recognize
+from deepresearch_flow.translator.cli import translator
 
 
 @click.group()
@@ -13,6 +14,7 @@ def cli() -> None:
 
 cli.add_command(paper)
 cli.add_command(recognize)
+cli.add_command(translator)
 
 
 def main() -> None:

{deepresearch_flow-0.2.1 → deepresearch_flow-0.4.0}/python/deepresearch_flow/paper/config.py

@@ -40,6 +40,7 @@ class ProviderConfig:
     location: str | None
     credentials_path: str | None
     anthropic_version: str | None
+    max_tokens: int | None
     structured_mode: str
     extra_headers: dict[str, str]
     system_prompt: str | None
@@ -102,6 +103,15 @@ def _as_str(value: Any, default: str | None = None) -> str | None:
     return str(value)
 
 
+def _ensure_http_scheme(base_url: str, *, default_scheme: str = "http://") -> str:
+    normalized = base_url.strip()
+    if normalized.startswith(("http://", "https://")):
+        scheme, rest = normalized.split("://", 1)
+        rest = rest.lstrip("/")
+        return f"{scheme}://{rest}" if rest else f"{scheme}://"
+    return f"{default_scheme}{normalized.lstrip('/')}"
+
+
 def load_config(path: str) -> PaperConfig:
     config_path = Path(path)
     if not config_path.exists():
@@ -158,6 +168,8 @@ def load_config(path: str) -> PaperConfig:
                 raise ValueError(f"Provider '{name}' requires base_url")
         elif provider_type == "azure_openai" and endpoint:
             base_url = endpoint
+        if provider_type == "ollama" and base_url:
+            base_url = _ensure_http_scheme(base_url)
 
         api_keys = _as_list(provider.get("api_keys"))
         if not api_keys:
@@ -188,6 +200,8 @@ def load_config(path: str) -> PaperConfig:
         location = _as_str(provider.get("location"), None)
         credentials_path = _as_str(provider.get("credentials_path"), None)
         anthropic_version = _as_str(provider.get("anthropic_version"), None)
+        max_tokens = provider.get("max_tokens")
+        max_tokens_value = int(max_tokens) if max_tokens is not None else None
 
         if provider_type == "azure_openai":
             if not base_url:
@@ -221,6 +235,7 @@ def load_config(path: str) -> PaperConfig:
                 location=location,
                 credentials_path=credentials_path,
                 anthropic_version=anthropic_version,
+                max_tokens=max_tokens_value,
                 structured_mode=structured_mode,
                 extra_headers=extra_headers,
                 system_prompt=_as_str(provider.get("system_prompt"), None),