Merge pull request #7 from stackhpc/upstream-v0.19.1

Update to upstream v0.19.1

Author: sd109

.github/workflows/tests.yml

@@ -88,7 +88,12 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && uv pip install . && source .venv/bin/activate && cd test/test_sdk_api && pytest -s --tb=short get_email.py t_dataset.py t_chat.py t_session.py t_document.py t_chunk.py
+          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+            export HTTP_API_TEST_LEVEL=p3
+          else
+            export HTTP_API_TEST_LEVEL=p2
+          fi
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python && uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
 
       - name: Run frontend api tests against Elasticsearch
         run: |
@@ -98,7 +103,7 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
+          cd sdk/python && UV_LINK_MODE=copy uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
           
       - name: Run http api tests against Elasticsearch
         run: |
@@ -113,7 +118,7 @@ jobs:
           else
             export HTTP_API_TEST_LEVEL=p2
           fi
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_http_api && pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL}
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
 
       - name: Stop ragflow:nightly
         if: always()  # always run this step even if previous steps failed
@@ -132,7 +137,12 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && uv pip install . && source .venv/bin/activate && cd test/test_sdk_api && pytest -s --tb=short get_email.py t_dataset.py t_chat.py t_session.py t_document.py t_chunk.py
+          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+            export HTTP_API_TEST_LEVEL=p3
+          else
+            export HTTP_API_TEST_LEVEL=p2
+          fi
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python && DOC_ENGINE=infinity uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
 
       - name: Run frontend api tests against Infinity
         run: |
@@ -142,7 +152,7 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
+          cd sdk/python && UV_LINK_MODE=copy uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
 
       - name: Run http api tests against Infinity
         run: |
@@ -157,7 +167,7 @@ jobs:
           else
             export HTTP_API_TEST_LEVEL=p2
           fi
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_http_api && DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL}
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && DOC_ENGINE=infinity uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
 
       - name: Stop ragflow:nightly
         if: always()  # always run this step even if previous steps failed

.gitignore

@@ -36,6 +36,12 @@ sdk/python/ragflow.egg-info/
 sdk/python/build/
 sdk/python/dist/
 sdk/python/ragflow_sdk.egg-info/
+
+# Exclude dep files
+libssl*.deb
+tika-server*.jar*
+cl100k_base.tiktoken
+chrome*
 huggingface.co/
 nltk_data/
 
@@ -44,3 +50,146 @@ nltk_data/
 .lh/
 .venv
 docker/data
+
+
+#--------------------------------------------------#
+# The following was generated with gitignore.nvim: #
+#--------------------------------------------------#
+# Gitignore for the following technologies: Node
+
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+# Comment in the public line in if your project uses Gatsby and not Next.js
+# https://nextjs.org/blog/next-9-1#public-directory-support
+# public
+
+# vuepress build output
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+.temp
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v2
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
+
+# Serverless Webpack directories
+.webpack/
+
+# SvelteKit build / generate output
+.svelte-kit
+

README.md

@@ -5,13 +5,13 @@
 </div>
 
 <p align="center">
-  <a href="./README.md">English</a> |
-  <a href="./README_zh.md">简体中文</a> |
-  <a href="./README_tzh.md">繁体中文</a> |
-  <a href="./README_ja.md">日本語</a> |
-  <a href="./README_ko.md">한국어</a> |
-  <a href="./README_id.md">Bahasa Indonesia</a> |
-  <a href="/README_pt_br.md">Português (Brasil)</a>
+  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-DBEDFA"></a>
+  <a href="./README_zh.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
+  <a href="./README_tzh.md"><img alt="繁體版中文自述文件" src="https://img.shields.io/badge/繁體中文-DFE0E5"></a>
+  <a href="./README_ja.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-DFE0E5"></a>
+  <a href="./README_ko.md"><img alt="한국어" src="https://img.shields.io/badge/한국어-DFE0E5"></a>
+  <a href="./README_id.md"><img alt="Bahasa Indonesia" src="https://img.shields.io/badge/Bahasa Indonesia-DFE0E5"></a>
+  <a href="./README_pt_br.md"><img alt="Português(Brasil)" src="https://img.shields.io/badge/Português(Brasil)-DFE0E5"></a>
 </p>
 
 <p align="center">
@@ -22,14 +22,17 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/badge/docker_pull-ragflow:v0.19.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.19.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.19.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
     </a>
     <a href="https://github.com/infiniflow/ragflow/blob/main/LICENSE">
         <img height="21" src="https://img.shields.io/badge/License-Apache--2.0-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="license">
     </a>
+    <a href="https://deepwiki.com/infiniflow/ragflow">
+        <img alt="Ask DeepWiki" src="https://deepwiki.com/badge.svg">
+    </a>
 </p>
 
 <h4 align="center">
@@ -40,6 +43,12 @@
   <a href="https://demo.ragflow.io">Demo</a>
 </h4>
 
+#
+
+<div align="center">
+<a href="https://trendshift.io/repositories/9064" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9064" alt="infiniflow%2Fragflow | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</div>
+
 <details open>
 <summary><b>📕 Table of Contents</b></summary>
 
@@ -78,11 +87,11 @@ Try our demo at [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Latest Updates
 
+- 2025-05-23 Adds a Python/JavaScript code executor component to Agent.
+- 2025-05-05 Supports cross-language query.
 - 2025-03-19 Supports using a multi-modal model to make sense of images within PDF or DOCX files.
 - 2025-02-28 Combined with Internet search (Tavily), supports reasoning like Deep Research for any LLMs.
-- 2025-01-26 Optimizes knowledge graph extraction and application, offering various configuration options.
 - 2024-12-18 Upgrades Document Layout Analysis model in DeepDoc.
-- 2024-11-01 Adds keyword extraction and related question generation to the parsed chunks to improve the accuracy of retrieval.
 - 2024-08-22 Support text to SQL statements through RAG.
 
 ## 🎉 Stay Tuned
@@ -178,7 +187,7 @@ releases! 🌟
 > All Docker images are built for x86 platforms. We don't currently offer Docker images for ARM64.
 > If you are on an ARM64 platform, follow [this guide](https://ragflow.io/docs/dev/build_docker_image) to build a Docker image compatible with your system.
 
-   > The command below downloads the `v0.19.0-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.19.0-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.19.0` for the full edition `v0.19.0`.
+   > The command below downloads the `v0.19.1-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.19.1-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.19.1` for the full edition `v0.19.1`.
 
    ```bash
    $ cd ragflow/docker
@@ -191,8 +200,8 @@ releases! 🌟
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    |-------------------|-----------------|-----------------------|--------------------------|
-   | v0.19.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.19.0-slim      | &approx;2       | ❌                   | Stable release            |
+   | v0.19.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.19.1-slim      | &approx;2       | ❌                   | Stable release            |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                   | _Unstable_ nightly build  |
 

README_id.md

@@ -5,13 +5,13 @@
 </div>
 
 <p align="center">
-  <a href="./README.md">English</a> |
-  <a href="./README_zh.md">简体中文</a> |
-  <a href="./README_tzh.md">繁体中文</a> |
-  <a href="./README_ja.md">日本語</a> |
-  <a href="./README_ko.md">한국어</a> |
-  <a href="./README_id.md">Bahasa Indonesia</a> |
-  <a href="/README_pt_br.md">Português (Brasil)</a>
+  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
+  <a href="./README_zh.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
+  <a href="./README_tzh.md"><img alt="繁體中文版自述文件" src="https://img.shields.io/badge/繁體中文-DFE0E5"></a>
+  <a href="./README_ja.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-DFE0E5"></a>
+  <a href="./README_ko.md"><img alt="한국어" src="https://img.shields.io/badge/한국어-DFE0E5"></a>
+  <a href="./README_id.md"><img alt="Bahasa Indonesia" src="https://img.shields.io/badge/Bahasa Indonesia-DBEDFA"></a>
+  <a href="./README_pt_br.md"><img alt="Português(Brasil)" src="https://img.shields.io/badge/Português(Brasil)-DFE0E5"></a>
 </p>
 
 <p align="center">
@@ -22,14 +22,17 @@
         <img alt="Lencana Daring" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/badge/docker_pull-ragflow:v0.19.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.19.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.19.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Rilis%20Terbaru" alt="Rilis Terbaru">
     </a>
     <a href="https://github.com/infiniflow/ragflow/blob/main/LICENSE">
         <img height="21" src="https://img.shields.io/badge/Lisensi-Apache--2.0-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="Lisensi">
     </a>
+    <a href="https://deepwiki.com/infiniflow/ragflow">
+        <img alt="Ask DeepWiki" src="https://deepwiki.com/badge.svg">
+    </a>
 </p>
 
 <h4 align="center">
@@ -40,6 +43,8 @@
   <a href="https://demo.ragflow.io">Demo</a>
 </h4>
 
+#
+
 <details open>
 <summary><b>📕 Daftar Isi </b> </summary>
 
@@ -75,11 +80,11 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Pembaruan Terbaru
 
+- 2025-05-23 Menambahkan komponen pelaksana kode Python/JS ke Agen.
+- 2025-05-05 Mendukung kueri lintas bahasa.
 - 2025-03-19 Mendukung penggunaan model multi-modal untuk memahami gambar di dalam file PDF atau DOCX.
 - 2025-02-28 dikombinasikan dengan pencarian Internet (TAVILY), mendukung penelitian mendalam untuk LLM apa pun.
-- 2025-01-26 Optimalkan ekstraksi dan penerapan grafik pengetahuan dan sediakan berbagai opsi konfigurasi.
 - 2024-12-18 Meningkatkan model Analisis Tata Letak Dokumen di DeepDoc.
-- 2024-11-01 Penambahan ekstraksi kata kunci dan pembuatan pertanyaan terkait untuk meningkatkan akurasi pengambilan.
 - 2024-08-22 Dukungan untuk teks ke pernyataan SQL melalui RAG.
 
 ## 🎉 Tetap Terkini
@@ -173,7 +178,7 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 > Semua gambar Docker dibangun untuk platform x86. Saat ini, kami tidak menawarkan gambar Docker untuk ARM64.
 > Jika Anda menggunakan platform ARM64, [silakan gunakan panduan ini untuk membangun gambar Docker yang kompatibel dengan sistem Anda](https://ragflow.io/docs/dev/build_docker_image).
 
-> Perintah di bawah ini mengunduh edisi v0.19.0-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.19.0-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.19.0 untuk edisi lengkap v0.19.0.
+> Perintah di bawah ini mengunduh edisi v0.19.1-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.19.1-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.19.1 untuk edisi lengkap v0.19.1.
 
 ```bash
 $ cd ragflow/docker
@@ -186,8 +191,8 @@ $ docker compose -f docker-compose.yml up -d
 
 | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
 | ----------------- | --------------- | --------------------- | ------------------------ |
-| v0.19.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-| v0.19.0-slim      | &approx;2       | ❌                    | Stable release           |
+| v0.19.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+| v0.19.1-slim      | &approx;2       | ❌                    | Stable release           |
 | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
 | nightly-slim      | &approx;2       | ❌                    | _Unstable_ nightly build |