docs(reading-audio-tool): update docs for reading and audio tools

docs/mkdocs/docs/hle.md

@@ -2,7 +2,7 @@
 
 MiroFlow's evaluation on the HLE benchmark demonstrates capabilities in multimodal reasoning and question answering tasks that require human-level understanding across vision and language.
 
-More details: [HLE Dataset on HuggingFace](https://huggingface.co/datasets/cais/hle)
+More details: [Humanity's Last Exam](https://arxiv.org/abs/2501.14249)
 
 ---
 

docs/mkdocs/docs/index.md

@@ -18,10 +18,11 @@
 
     **Oct 2025** - 
 
-    - Add support for Index
-    - Add support for BrowseComp-EN evaluation
-    - Add support for MiroAPI https://github.com/MiroMindAI/MiroFlow/pull/76
-
+
+    - 📝 Added support for HLE-Text evaluation benchmark [#81](https://github.com/MiroMindAI/MiroFlow/pull/81)
+    - 🧠 Added support for HLE (Humanity's Last Exam) benchmark [#79](https://github.com/MiroMindAI/MiroFlow/pull/79)
+    - 🌐 Added support for BrowseComp-EN evaluation benchmark [#78](https://github.com/MiroMindAI/MiroFlow/pull/78)
+    - 🔌 Added support for MiroAPI integration [#76](https://github.com/MiroMindAI/MiroFlow/pull/76)
 
     - 📊 Added support for FinSearchComp evaluation benchmark [#51](https://github.com/MiroMindAI/MiroFlow/pull/51)
     - 🔍 Added support for XBench-DS (Deep Search) evaluation [#47](https://github.com/MiroMindAI/MiroFlow/pull/47)

docs/mkdocs/docs/tool_audio.md

@@ -0,0 +1,90 @@
+# Audio Tools (`tool-audio`)
+
+Audio processing capabilities including transcription and audio-based question answering.
+
+---
+
+## Configuration
+
+```yaml title="Agent Configuration"
+main_agent:
+  tool_config: 
+    - tool-audio
+```
+
+**Environment Variables:**
+
+- `OPENAI_API_KEY`: **Required**. OpenAI API key
+- `OPENAI_BASE_URL`: API base URL. Default: `https://api.openai.com/v1`
+- `OPENAI_TRANSCRIPTION_MODEL_NAME`: Default: `gpt-4o-transcribe`
+- `OPENAI_AUDIO_MODEL_NAME`: Default: `gpt-4o-audio-preview`
+
+---
+
+## Function Reference
+
+### `audio_transcription(audio_path_or_url: str)`
+
+Transcribe audio file to text using OpenAI's Whisper models.
+
+**Parameters:**
+
+- `audio_path_or_url`: Local file path or URL
+  - Supported formats: MP3, WAV, M4A, FLAC, OGG, WebM
+  - Not supported: E2B sandbox paths, YouTube URLs
+
+**Returns:**
+
+- `str`: Full transcription of the audio file
+
+**Example:**
+
+```python
+# Transcribe local audio
+transcription = await audio_transcription("/data/meeting.mp3")
+
+# Transcribe from URL
+transcription = await audio_transcription("https://example.com/podcast.wav")
+```
+
+---
+
+### `audio_question_answering(audio_path_or_url: str, question: str)`
+
+Answer questions based on audio content using GPT-4o Audio.
+
+**Parameters:**
+
+- `audio_path_or_url`: Local file path or URL (same formats as transcription)
+- `question`: Question to answer about the audio content
+
+**Returns:**
+
+- `str`: Answer with audio duration information
+
+**Example:**
+
+```python
+# Ask about content
+answer = await audio_question_answering(
+    "/data/lecture.mp3", 
+    "What are the main topics discussed?"
+)
+
+# Get summary
+answer = await audio_question_answering(
+    "https://example.com/interview.wav",
+    "Summarize the key points."
+)
+```
+
+**Important Notes:**
+
+- Cannot access E2B sandbox files (`/home/user/`)
+- YouTube URLs not supported (use VQA tools instead)
+- Includes audio duration in response
+
+---
+
+!!! info "Documentation Info"
+    **Last Updated:** October 2025 · **Doc Contributor:** Team @ MiroMind AI

docs/mkdocs/docs/tool_reading.md

@@ -0,0 +1,71 @@
+# Reading Tools (`tool-reading`)
+
+Read and convert various document formats (DOC, PDF, Excel, etc.) to markdown for easy processing.
+
+---
+
+## Configuration
+
+```yaml title="Agent Configuration"
+main_agent:
+  tool_config: 
+    - tool-reading
+```
+
+**Environment Variables:**
+
+- `SERPER_API_KEY`: Required for certain operations
+- `JINA_API_KEY`: Required for document processing
+
+---
+
+## Function Reference
+
+### `read_file(uri: str)`
+
+Read various types of resources and convert them to markdown format.
+
+**Parameters:**
+
+- `uri`: The URI or path of the resource to read. Supported:
+  - Local file paths (e.g., `/path/to/document.pdf`)
+  - `file:` URIs (e.g., `file:/path/to/document.pdf`)
+  - `http:` / `https:` URLs (will be downloaded automatically)
+  - `data:` URIs (base64-encoded)
+
+**Supported Formats:**
+
+- Documents: DOC, DOCX, RTF, ODT
+- Presentations: PPT, PPTX, ODP
+- Spreadsheets: XLS, XLSX, CSV, ODS
+- PDFs: PDF documents
+- Archives: ZIP files
+- Images and text files
+
+**Returns:**
+
+- `str`: Content in markdown format, or error message if reading fails
+
+**Example:**
+
+```python
+# Read a local PDF
+result = await read_file("file:/path/to/document.pdf")
+
+# Read from URL
+result = await read_file("https://example.com/report.pdf")
+
+# Read local file (auto-converted to file: URI)
+result = await read_file("/data/spreadsheet.xlsx")
+```
+
+**Important Notes:**
+
+- Cannot access E2B sandbox files (`/home/user/`)
+- Use local file paths provided in the original instruction
+- Downloaded files are automatically cleaned up
+
+---
+
+!!! info "Documentation Info"
+    **Last Updated:** October 2025 · **Doc Contributor:** Team @ MiroMind AI

docs/mkdocs/docs/tool_searching_serper.md

@@ -0,0 +1,92 @@
+# Searching Tools - Serper (`tool-searching-serper`)
+
+Lightweight Google search and web scraping via Serper API using NPM package.
+
+!!! tip "Which Tool to Use?"
+    - **`tool-searching-serper`**: Fast Google search + basic scraping (NPM-based)
+    - **`tool-searching`**: Full-featured with Wikipedia, Archive.org, JINA (Python-based)
+
+---
+
+## Configuration
+
+```yaml title="Agent Configuration"
+main_agent:
+  tool_config: 
+    - tool-searching-serper
+```
+
+**Environment Variables:**
+
+- `SERPER_API_KEY`: **Required**. Get at [serper.dev](https://serper.dev)
+
+---
+
+## Function Reference
+
+### `google_search(q: str, gl: str = "us", hl: str = "en", location: str = None, num: int = 10, tbs: str = None, page: int = 1)`
+
+Perform Google searches via Serper API.
+
+**Parameters:**
+
+- `q`: Search query (required)
+- `gl`: Country code (e.g., 'us', 'uk', 'cn'). Default: 'us'
+- `hl`: Language (e.g., 'en', 'zh', 'es'). Default: 'en'
+- `location`: City location (e.g., 'San Francisco, California, United States')
+- `num`: Number of results. Default: 10
+- `tbs`: Time filter ('qdr:h'=hour, 'qdr:d'=day, 'qdr:w'=week, 'qdr:m'=month, 'qdr:y'=year)
+- `page`: Page number. Default: 1
+
+**Returns:**
+
+- `str`: JSON formatted search results
+
+**Example:**
+
+```python
+# Basic search
+results = await google_search("artificial intelligence")
+
+# With filters
+results = await google_search("latest news", tbs="qdr:d", num=20)
+```
+
+---
+
+### `scrape(url: str)`
+
+Scrape website content using Serper.
+
+**Parameters:**
+
+- `url`: Website URL to scrape
+
+**Returns:**
+
+- `str`: Scraped content
+
+**Example:**
+
+```python
+content = await scrape("https://example.com/article")
+```
+
+---
+
+## Comparison: Serper vs Full Searching
+
+| Feature | `tool-searching-serper` | `tool-searching` |
+|---------|------------------------|------------------|
+| Google Search | ✅ | ✅ |
+| Web Scraping | ✅ Basic | ✅ Advanced |
+| Wikipedia | ❌ | ✅ |
+| Archive.org | ❌ | ✅ |
+| YouTube Info | ❌ | ✅ |
+| Speed | ⚡ Faster | Slightly slower |
+| Dependencies | Node.js/NPM | Python only |
+
+---
+
+!!! info "Documentation Info"
+    **Last Updated:** October 2025 · **Doc Contributor:** Team @ MiroMind AI

docs/mkdocs/mkdocs.yml

@@ -65,16 +65,7 @@ nav:
     - xBench-DeepSearch: xbench_ds.md
     - FinSearchComp: finsearchcomp.md
     - HLE: hle.md
-    - HLE(text only): hle_text_only.md
-
-    # - Benchmarks: 
-    #   - GAIA-Validation-Text-Only: gaia_validation_text_only.md
-    #   - GAIA-Test: gaia_test.md
-    #   - BrowseComp-EN: browsecomp_en.md
-    #   - FutureX: futurex.md
-    #   - xBench-DeepSearch: xbench_ds.md
-    #   - FinSearchComp: finsearchcomp.md
-    # - Download Datasets: download_datasets.md
+    - HLE-Text-Only: hle_text_only.md
 
 
 
@@ -85,12 +76,15 @@ nav:
     - "": ""
     - "": ""
     - "": ""
+    - tool-reading: tool_reading.md
+    - tool-searching: tool_searching.md
+    - tool-searching-serper: tool_searching_serper.md
+    - tool-audio: tool_audio.md
+    - tool-audio-os: tool_audio_os.md
     - tool-reasoning: tool_reasoning.md
     - tool-reasoning-os: tool_reasoning_os.md
     - tool-image-video: tool_vqa.md
     - tool-image-video-os: tool_vqa_os.md
-    - tool-audio-os: tool_audio_os.md
-    - tool-searching: tool_searching.md
     - tool-python: tool_python.md
     - "": ""
     - "": ""