### What problem does this PR solve?
- Added support for S3-compatible protocols.
- Enabled the use of knowledge base ID as a file prefix when storing
files in S3.
- Updated docker/README.md to include detailed S3 and OSS configuration
instructions.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/6138
This PR is going to support vision llm for gpustack, modify url path
from `/v1-openai` to `/v1`
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
### Type of change
- [x] Documentation Update
---------
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
### What problem does this PR solve?
Fix#6334
Hello, I encountered the same problem in #6334. In the
`api/db/db_models.py`, it calls `obj.create_table()` unconditionally in
`init_database_tables`, before the `migrate_db()`. Specially for the
`permission` field of `user_canvas` table, it has `index=True`, which
causes `peewee` to issue a SQL trying to create the index when the field
does not exist (the `user_canvas` table already exists), so
`psycopg2.errors.UndefinedColumn: column "permission" does not exist`
occurred.
I've added a judgement in the code, to only call `create_table()` when
the table does not exist, delegate the migration process to
`migrate_db()`.
Then another problem occurs: the `migrate_db()` actually does nothing
because it failed on the first migration! The `playhouse` blindly issue
DDLs without things like `IF NOT EXISTS`, so it fails... even if the
exception is `pass`, the transaction is still rolled back. So I removed
the transaction in `migrate_db()` to make it work.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Actually fix#6241
Hello, I ran into the same problem as #6241. When I'm testing my agent
flow in the web ui using `Run` button with a file input, the retrieval
component always gave an empty output.
In the code I found that:
`web/src/pages/flow/debug-content/index.tsx`:
```tsx
const onOk = useCallback(async () => {
const values = await form.validateFields();
const nextValues = Object.entries(values).map(([key, value]) => {
const item = parameters[Number(key)];
let nextValue = value;
if (Array.isArray(value)) {
nextValue = ``;
value.forEach((x) => {
nextValue +=
x?.originFileObj instanceof File
? `${x.name}\n${x.response?.data}\n----\n` // Here, the file content always ends in '\n'
: `${x.url}\n${x.result}\n----\n`;
});
}
return { ...item, value: nextValue };
});
ok(nextValues);
}, [form, ok, parameters]);
```
while in the `agent/component/retrieval.py`:
```python
def _run(self, history, **kwargs):
query = self.get_input()
query = str(query["content"][0]) if "content" in query else ""
lines = query.split('\n') # inputs are split to ['xxx','yyy','----','']
query = lines[-1] if lines else "" # Here we always get '', thus no result
kbs = KnowledgebaseService.get_by_ids(self._param.kb_ids)
if not kbs:
return Retrieval.be_output("")
```
so the code will never got correct result.
I'm not sure why the input needs such a split here, so I just removed
the splitting, and it works well on my side.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Fix#5418
Actually, the fix#4329 also works for agent flows with parameters, so
this PR just relaxes the `else` branch of that. With this PR, it works
fine on my side, may need more testing to make sure this does not break
something.
I guess the real problem may be deeply hidden in the code which relates
to conversation and canvas execution. After a few hours of debugging, I
see the only difference between with and without parameters in `begin`
component, is the `history` field of canvas data. When the `begin`
component contains some parameters, the debug log shows:
```
025-03-29 19:50:38,521 DEBUG 356590 {
"component_name": "Begin",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [{"type": "fileUrls", "key": "fileUrls", "name": "files", "optional": true, "value": "问题.txt\n今天天气怎么样"}], "inputs": [], "debug_inputs": [], "prologue": "你好！ 我是你的助理，有什么可以帮到你的吗？", "output": null},
"output": null,
"inputs": []
}, history: [["user", "请回答我上传文件中的问题。"]], kwargs: {"stream": false}
2025-03-29 19:50:38,523 DEBUG 356590 {
"component_name": "Answer",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [], "inputs": [], "debug_inputs": [], "post_answers": [], "output": null},
"output": null,
"inputs": []
}, history: [["user", "请回答我上传文件中的问题。"]], kwargs: {"stream": false}
```
Then it does not go further along the flow.
When the `begin` component does not contain any parameter, the debug log
shows:
```
2025-03-29 19:41:13,518 DEBUG 353596 {
"component_name": "Begin",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [], "inputs": [], "debug_inputs": [], "prologue": "你好！ 我是你的助理，有什么可以帮到你的吗？", "output": null},
"output": null,
"inputs": []
}, history: [], kwargs: {"stream": false}
2025-03-29 19:41:13,520 DEBUG 353596 {
"component_name": "Answer",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [], "inputs": [], "debug_inputs": [], "post_answers": [], "output": null},
"output": null,
"inputs": []
}, history: [], kwargs: {"stream": false}
2025-03-29 19:41:13,556 INFO 353596 127.0.0.1 - - [29/Mar/2025 19:41:13] "POST /api/v1/agents/fee6886a0c6f11f09b48eb8798e9aa9b/sessions?user_id=123 HTTP/1.1" 200 -
2025-03-29 19:41:21,115 DEBUG 353596 Canvas.prepare2run: Retrieval:LateGuestsNotice
2025-03-29 19:41:21,116 DEBUG 353596 {
"component_name": "Retrieval",
"params": {"output_var_name": "output", "message_history_window_size": 22, "query": [], "inputs": [], "debug_inputs": [], "similarity_threshold": 0.2, "keywords_similarity_weight": 0.3, "top_n": 8, "top_k": 1024, "kb_ids": ["9aca3c700c5911f0811caf35658b9385"], "rerank_id": "", "empty_response": "", "tavily_api_key": "", "use_kg": false, "output": null},
"output": null,
"inputs": []
}, history: [["user", "请回答我上传文件中的问题。"]], kwargs: {"stream": false}
```
It correctly goes along the flow and generates correct answer.
You can see the difference: when the `begin` component has any
parameter, the `history` field is filled from the beginning, while it is
just `[]` if the `begin` component has no parameter.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Fix knowledge_graph_kwd on infinity. Close#6476 and #6624
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix entity_types. Close#6287 and #6608
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR gives better control over how we distribute which service will
be loaded. With this approach, we can create containers to run only the
web server and others to run the task executor. It also introduces the
unique ID per task executor host, this will be important when scaling
task executors horizontally, considering unique task executor ids will
be required.
This new `entrypoint.sh` maintains the default behavior of starting the
web server and task executor in the same host.
### 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):
# Dynamic Context Window Size for Ollama Chat
## Problem Statement
Previously, the Ollama chat implementation used a fixed context window
size of 32768 tokens. This caused two main issues:
1. Performance degradation due to unnecessarily large context windows
for small conversations
2. Potential business logic failures when using smaller fixed sizes
(e.g., 2048 tokens)
## Solution
Implemented a dynamic context window size calculation that:
1. Uses a base context size of 8192 tokens
2. Applies a 1.2x buffer ratio to the total token count
3. Adds multiples of 8192 tokens based on the buffered token count
4. Implements a smart context size update strategy
## Implementation Details
### Token Counting Logic
```python
def count_tokens(text):
"""Calculate token count for text"""
# Simple calculation: 1 token per ASCII character
# 2 tokens for non-ASCII characters (Chinese, Japanese, Korean, etc.)
total = 0
for char in text:
if ord(char) < 128: # ASCII characters
total += 1
else: # Non-ASCII characters
total += 2
return total
```
### Dynamic Context Calculation
```python
def _calculate_dynamic_ctx(self, history):
"""Calculate dynamic context window size"""
# Calculate total tokens for all messages
total_tokens = 0
for message in history:
content = message.get("content", "")
content_tokens = count_tokens(content)
role_tokens = 4 # Role marker token overhead
total_tokens += content_tokens + role_tokens
# Apply 1.2x buffer ratio
total_tokens_with_buffer = int(total_tokens * 1.2)
# Calculate context size in multiples of 8192
if total_tokens_with_buffer <= 8192:
ctx_size = 8192
else:
ctx_multiplier = (total_tokens_with_buffer // 8192) + 1
ctx_size = ctx_multiplier * 8192
return ctx_size
```
### Integration in Chat Method
```python
def chat(self, system, history, gen_conf):
if system:
history.insert(0, {"role": "system", "content": system})
if "max_tokens" in gen_conf:
del gen_conf["max_tokens"]
try:
# Calculate new context size
new_ctx_size = self._calculate_dynamic_ctx(history)
# Prepare options with context size
options = {
"num_ctx": new_ctx_size
}
# Add other generation options
if "temperature" in gen_conf:
options["temperature"] = gen_conf["temperature"]
if "max_tokens" in gen_conf:
options["num_predict"] = gen_conf["max_tokens"]
if "top_p" in gen_conf:
options["top_p"] = gen_conf["top_p"]
if "presence_penalty" in gen_conf:
options["presence_penalty"] = gen_conf["presence_penalty"]
if "frequency_penalty" in gen_conf:
options["frequency_penalty"] = gen_conf["frequency_penalty"]
# Make API call with dynamic context size
response = self.client.chat(
model=self.model_name,
messages=history,
options=options,
keep_alive=60
)
return response["message"]["content"].strip(), response.get("eval_count", 0) + response.get("prompt_eval_count", 0)
except Exception as e:
return "**ERROR**: " + str(e), 0
```
## Benefits
1. **Improved Performance**: Uses appropriate context windows based on
conversation length
2. **Better Resource Utilization**: Context window size scales with
content
3. **Maintained Compatibility**: Works with existing business logic
4. **Predictable Scaling**: Context growth in 8192-token increments
5. **Smart Updates**: Context size updates are optimized to reduce
unnecessary model reloads
## Future Considerations
1. Fine-tune buffer ratio based on usage patterns
2. Add monitoring for context window utilization
3. Consider language-specific token counting optimizations
4. Implement adaptive threshold based on conversation patterns
5. Add metrics for context size update frequency
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This PR updates the MySQL container configuration by setting the
parameter --binlog_expire_logs_seconds to 604800 seconds (7 days). This
change ensures that MySQL automatically purges binary logs older than 7
days, helping to conserve disk space and maintain precise log
management.
### 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] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Feat: Add RadioGroup component #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: When Excel is a formula, the parsed result is a formula, but cannot
be correctly parsed as a value type
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: tangyu <1@1.com>
### 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] add test cases
### What problem does this PR solve?
Introduced delete_knowledge_graph
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] Documentation Update
### What problem does this PR solve?
When I use the categorization operator, I find that if the keyword I
want to Categorize appears repeatedly in the input, then I cannot judge
the word that appears most frequently. Instead, I simply get the word
that matches and return all the ones that have made the following
changes to the categorize filter.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
- [x] Performance Improvement
### What problem does this PR solve?
Feat: Add logo-with-text-white.svg #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Prevent applications from failing to start due to calling non-existent
or incorrect Minio connection configurations when using file storage
outside of Minio
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
related issue #5882
### What problem does this PR solve?
update helm infinity image version from v0.5.0
image to infiniflow/infinity:v0.6.0-dev3
to solve issue #5882
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Fix:flow DB Assistant module translate to zh
### 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?
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Chenzy <chenzy901@gmail.com>
### What problem does this PR solve?
There is a small bug in the update dataset of this document. The return
type of rag_oobject.list_datasets is a list type, and the first item
should be taken as' ragflow_stdk.modules.dataset ' DataSet`， Adapt to
the update.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Removed set_entity and set_relation to avoid accessing doc engine during
graph computation.
Introduced GraphChange to avoid writing unchanged chunks.
### Type of change
- [x] Performance Improvement
### What problem does this PR solve?
1. for /mv API use get by ids to avoid O(n) DB IO
2. for /list remove one useless call
### Type of change
- [x] Performance Improvement
