### What problem does this PR solve?
feat: Add component Invoke #2908
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Turn resource to plural form
### Type of change
- [x] Refactoring
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
feat: Add hint for operators, round to square, input variable, readable operator ID. #3056 (#3057)
### What problem does this PR solve?
feat: Add hint for operators, round to square, input variable, readable
operator ID. #3056
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Turn resource to plural form
### Type of change
- [x] Refactoring
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
Bumps [werkzeug](https://github.com/pallets/werkzeug) from 3.0.3 to
3.0.6.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/pallets/werkzeug/releases">werkzeug's
releases</a>.</em></p>
<blockquote>
<h2>3.0.6</h2>
<p>This is the Werkzeug 3.0.6 security fix release, which fixes security
issues but does not otherwise change behavior and should not result in
breaking changes.</p>
<p>PyPI: <a
href="https://pypi.org/project/Werkzeug/3.0.6/">https://pypi.org/project/Werkzeug/3.0.6/</a>
Changes: <a
href="https://werkzeug.palletsprojects.com/en/stable/changes/#version-3-0-6">https://werkzeug.palletsprojects.com/en/stable/changes/#version-3-0-6</a></p>
<ul>
<li>Fix how <code>max_form_memory_size</code> is applied when parsing
large non-file fields. <a
href="https://github.com/advisories/GHSA-q34m-jh98-gwm2">GHSA-q34m-jh98-gwm2</a></li>
<li><code>safe_join</code> catches certain paths on Windows that were
not caught by <code>ntpath.isabs</code> on Python < 3.11. <a
href="https://github.com/advisories/GHSA-f9vj-2wh5-fj8j">GHSA-f9vj-2wh5-fj8j</a></li>
</ul>
<h2>3.0.5</h2>
<p>This is the Werkzeug 3.0.5 fix release, which fixes bugs but does not
otherwise change behavior and should not result in breaking changes.</p>
<p>PyPI: <a
href="https://pypi.org/project/Werkzeug/3.0.5/">https://pypi.org/project/Werkzeug/3.0.5/</a>
Changes: <a
href="https://werkzeug.palletsprojects.com/en/stable/changes/#version-3-0-5">https://werkzeug.palletsprojects.com/en/stable/changes/#version-3-0-5</a>
Milestone: <a
href="https://github.com/pallets/werkzeug/milestone/37?closed=1">https://github.com/pallets/werkzeug/milestone/37?closed=1</a></p>
<ul>
<li>The Watchdog reloader ignores file closed no write events. <a
href="https://redirect.github.com/pallets/werkzeug/issues/2945">#2945</a></li>
<li>Logging works with client addresses containing an IPv6 scope. <a
href="https://redirect.github.com/pallets/werkzeug/issues/2952">#2952</a></li>
<li>Ignore invalid authorization parameters. <a
href="https://redirect.github.com/pallets/werkzeug/issues/2955">#2955</a></li>
<li>Improve type annotation fore <code>SharedDataMiddleware</code>. <a
href="https://redirect.github.com/pallets/werkzeug/issues/2958">#2958</a></li>
<li>Compatibility with Python 3.13 when generating debugger pin and the
current UID does not have an associated name. <a
href="https://redirect.github.com/pallets/werkzeug/issues/2957">#2957</a></li>
</ul>
<h2>3.0.4</h2>
<p>This is the Werkzeug 3.0.4 fix release, which fixes bugs but does not
otherwise change behavior and should not result in breaking changes.</p>
<p>PyPI: <a
href="https://pypi.org/project/Werkzeug/3.0.4/">https://pypi.org/project/Werkzeug/3.0.4/</a>
Changes: <a
href="https://werkzeug.palletsprojects.com/en/3.0.x/changes/#version-3-0-4">https://werkzeug.palletsprojects.com/en/3.0.x/changes/#version-3-0-4</a>
Milestone: <a
href="https://github.com/pallets/werkzeug/milestone/36?closed=1">https://github.com/pallets/werkzeug/milestone/36?closed=1</a></p>
<ul>
<li>Restore behavior where parsing
<code>multipart/x-www-form-urlencoded</code> data with
invalid UTF-8 bytes in the body results in no form data parsed rather
than a
413 error. <a
href="https://redirect.github.com/pallets/werkzeug/issues/2930">#2930</a></li>
<li>Improve <code>parse_options_header</code> performance when parsing
unterminated
quoted string values. <a
href="https://redirect.github.com/pallets/werkzeug/issues/2904">#2904</a></li>
<li>Debugger pin auth is synchronized across threads/processes when
tracking
failed entries. <a
href="https://redirect.github.com/pallets/werkzeug/issues/2916">#2916</a></li>
<li>Dev server handles unexpected <code>SSLEOFError</code> due to issue
in Python < 3.13.
<a
href="https://redirect.github.com/pallets/werkzeug/issues/2926">#2926</a></li>
<li>Debugger pin auth works when the URL already contains a query
string.
<a
href="https://redirect.github.com/pallets/werkzeug/issues/2918">#2918</a></li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/pallets/werkzeug/blob/main/CHANGES.rst">werkzeug's
changelog</a>.</em></p>
<blockquote>
<h2>Version 3.0.6</h2>
<p>Released 2024-10-25</p>
<ul>
<li>Fix how <code>max_form_memory_size</code> is applied when parsing
large non-file
fields. :ghsa:<code>q34m-jh98-gwm2</code></li>
<li><code>safe_join</code> catches certain paths on Windows that were
not caught by
<code>ntpath.isabs</code> on Python < 3.11.
:ghsa:<code>f9vj-2wh5-fj8j</code></li>
</ul>
<h2>Version 3.0.5</h2>
<p>Released 2024-10-24</p>
<ul>
<li>The Watchdog reloader ignores file closed no write events.
:issue:<code>2945</code></li>
<li>Logging works with client addresses containing an IPv6 scope
:issue:<code>2952</code></li>
<li>Ignore invalid authorization parameters.
:issue:<code>2955</code></li>
<li>Improve type annotation fore <code>SharedDataMiddleware</code>.
:issue:<code>2958</code></li>
<li>Compatibility with Python 3.13 when generating debugger pin and the
current
UID does not have an associated name. :issue:<code>2957</code></li>
</ul>
<h2>Version 3.0.4</h2>
<p>Released 2024-08-21</p>
<ul>
<li>Restore behavior where parsing
<code>multipart/x-www-form-urlencoded</code> data with
invalid UTF-8 bytes in the body results in no form data parsed rather
than a
413 error. :issue:<code>2930</code></li>
<li>Improve <code>parse_options_header</code> performance when parsing
unterminated
quoted string values. :issue:<code>2904</code></li>
<li>Debugger pin auth is synchronized across threads/processes when
tracking
failed entries. :issue:<code>2916</code></li>
<li>Dev server handles unexpected <code>SSLEOFError</code> due to issue
in Python < 3.13.
:issue:<code>2926</code></li>
<li>Debugger pin auth works when the URL already contains a query
string.
:issue:<code>2918</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="5eaefc3996"><code>5eaefc3</code></a>
release version 3.0.6</li>
<li><a
href="2767bcb10a"><code>2767bcb</code></a>
Merge commit from fork</li>
<li><a
href="87cc78a25f"><code>87cc78a</code></a>
catch special absolute path on Windows Python < 3.11</li>
<li><a
href="50cfeebcb0"><code>50cfeeb</code></a>
Merge commit from fork</li>
<li><a
href="8760275afb"><code>8760275</code></a>
apply max_form_memory_size another level up in the parser</li>
<li><a
href="8d6a12e2af"><code>8d6a12e</code></a>
start version 3.0.6</li>
<li><a
href="a7b121abc7"><code>a7b121a</code></a>
release version 3.0.5 (<a
href="https://redirect.github.com/pallets/werkzeug/issues/2961">#2961</a>)</li>
<li><a
href="9caf72ac06"><code>9caf72a</code></a>
release version 3.0.5</li>
<li><a
href="e28a2451e9"><code>e28a245</code></a>
catch OSError from getpass.getuser (<a
href="https://redirect.github.com/pallets/werkzeug/issues/2960">#2960</a>)</li>
<li><a
href="e6b4cce97e"><code>e6b4cce</code></a>
catch OSError from getpass.getuser</li>
<li>Additional commits viewable in <a
href="https://github.com/pallets/werkzeug/compare/3.0.3...3.0.6">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/infiniflow/ragflow/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Fix non-null violation when inviting people to team (#3015)
### What problem does this PR solve?
Not sure why MySQL is inserting empty string in this case, but when I
use postgres I got `null value in column "invited_by" of relation
"user_tenant" violates not-null constraint`
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix issues in API
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
### What problem does this PR solve?
Fix some issues in API and test
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Documentation Update
feat: Limit the maximum value of auto keywords to 30 #2687 (#2991)
### What problem does this PR solve?
feat: Limit the maximum value of auto keywords to 30 #2687
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Integrating RAGFlow API as a Plugin into ChatGPT-on-WeChat (#2988)
### What problem does this PR solve?
This PR introduces the `ragflow_chat` plugin for the ChatGPT-on-WeChat
project, extending its functionality by integrating Retrieval-Augmented
Generation (RAG) capabilities. It allows users to have more contextually
relevant conversations by retrieving information from external knowledge
sources (via the RAGFlow API) and incorporating it into their chat
interactions.
The primary goal of this PR is to enable seamless communication between
ChatGPT-on-WeChat and the RAGFlow server, improving response accuracy by
embedding knowledge-based data into conversational flows. This is
particularly useful for users who need more complex, data-driven
responses.
This PR adds a new plugin that enhances ChatGPT-on-WeChat with Ragflow
capabilities, allowing for a more enriched conversational experience
driven by external knowledge.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Documentation Update
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
allowing docker container to access service on host (#2895)
### What problem does this PR solve?
1. services running (e.g., ollama) running on the host could not be
accessed from docker containers
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
feat: Added auto_keywords and auto_questions fields to the parsing configuration page #2687 (#2987)
### What problem does this PR solve?
feat: Added auto_keywords and auto_questions fields to the parsing
configuration page #2687
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix some issues in API
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
[Bug]: unnecessary auto-increment calculations in the tokens statistics of the chat model (#2969)
### What problem does this PR solve?
the details is shown in
https://github.com/infiniflow/ragflow/issues/2968
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
make titles in markdown not be splited with following content (#2971)
### What problem does this PR solve?
#2970
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
[Bug]: When use OpenAI chat model , raise ERROR: 'CompletionUsage' object has no attribute 'get' #2948 (#2949)
[Bug]: When use OpenAI chat model , raise ERROR: 'CompletionUsage'
object has no attribute 'get' #2948
### What problem does this PR solve?
the detail of this PR is shown at
https://github.com/infiniflow/ragflow/issues/2948
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Fix some issues in API
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
### What problem does this PR solve?
1. fix: mid map show error in knowledge graph, juse because
```@antv/g6```version changed
2. feat: concurrent threads configuration support in graph extractor
3. fix: used tokens update failed for tenant
4. feat: timeout configuration support for llm
5. fix: regex error in graph extractor
6. feat: qwen rerank(```gte-rerank```) support
7. fix: timeout deal in knowledge graph index process. Now chat by
stream output, also, it is configuratable.
8. feat: ```qwen-long``` model configuration
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: chongchuanbing <chongchuanbing@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Add agent component for web crawler
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Resolves #2905 openai compatible model provider add llama.cpp rerank support (#2906)
### What problem does this PR solve?
Resolve #2905
due to the in-consistent of token size, I make it safe to limit 500 in
code, since there is no config param to control
my llama.cpp run set -ub to 1024:
${llama_path}/bin/llama-server --host 0.0.0.0 --port 9901 -ub 1024 -ngl
99 -m $gguf_file --reranking "$@"
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Here is my test Ragflow use llama.cpp
```
lot update_slots: id 0 | task 458 | prompt done, n_past = 416, n_tokens = 416
slot release: id 0 | task 458 | stop processing: n_past = 416, truncated = 0
slot launch_slot_: id 0 | task 459 | processing task
slot update_slots: id 0 | task 459 | tokenizing prompt, len = 2
slot update_slots: id 0 | task 459 | prompt tokenized, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 111
slot update_slots: id 0 | task 459 | kv cache rm [0, end)
slot update_slots: id 0 | task 459 | prompt processing progress, n_past = 111, n_tokens = 111, progress = 1.000000
slot update_slots: id 0 | task 459 | prompt done, n_past = 111, n_tokens = 111
slot release: id 0 | task 459 | stop processing: n_past = 111, truncated = 0
srv update_slots: all slots are idle
request: POST /rerank 172.23.0.4 200
```
Kevin Hu
balibabu
liuhua
dependabot[bot]
writinwaters
Brody Wang
david
Jin Hai
Hui Peng
Yinquan WANG
wwwlll
chongchuanbing
Ziyu Huang