### 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)
# 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>
### 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>
### 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?
When using the online large model API knowledge base to extract
knowledge graphs, frequent Rate Limit Errors were triggered,
causing document parsing to fail. This commit fixes the issue by
optimizing API calls in the following way:
Added exponential backoff and jitter to the API call to reduce the
frequency of Rate Limit Errors.
### 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?
Adds hierarchical title path tracking for tables in DOCX documents to
improve context association. Previously, extracted tables lacked
positional context within document structure.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix the error where the Ollama embeddings interface returns a “500
Internal Server Error” when using models such as xiaobu-embedding-v2 for
embedding.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Call register_scripts on connecting redis
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add fallback for PDF figure parser
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Optimize setting configuration initialization to resolve Minio
initialization error caused by using a specific storage.
Reproduction Scenario:
Using Aliyun OSS as the backend storage with the STORAGE_IMPL
environment variable set to OSS.
The service_conf.yaml.template configuration file contains OSS-related
configurations, while other storage configurations are commented out.
When the service starts, it still attempts to initialize the Minio
storage. Since there is no Minio configuration in
service_conf.yaml.template, it results in an error due to the missing
configuration file.
Optimization Measures:
Automatically determine the required initialization configuration based
on the environment variable.
Do not initialize configurations for unused resources.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add VLM-boosted PDF parser if VLM is set.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
When using LLM for auto-tag, if there are no examples, the tag format
generated by LLM may be wrong. This will cause Elasticsearch insert
errors. Adding basic examples can avoid this problem.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add vision LLM PDF parser
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Regards kb_id at ElasticSearch insert, update, delete. Close#6066
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
…ions
### What problem does this PR solve?
This PR fixes an issue where the application was repeatedly reading the
llm_factories.json file from disk in multiple places, which could lead
to "Too many open files" errors under high load conditions. The fix
centralizes the file reading operation in the settings.py module and
stores the data in a global variable that can be accessed by other
modules.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [x] Performance Improvement
- [ ] Other (please describe):
