Change: Instead of truncating texts, now using intelligent chunking:
1. Content ≤ 20,000 characters: Single embedding (complete)
2. Content > 20,000 characters: Split into 20k chunks
- Each chunk gets its own embedding
- All embeddings are averaged
- No information loss!
Benefits:
- No more text truncation
- Full information preserved
- Stays under 8192 token limit (nomic-embed-text)
- Average embedding represents entire text
Affected files:
- rdagent/components/knowledge_management/vector_base.py
Problem: Knowledge Graph versucht zu lange Texte zu embedden
- nomic-embed-text Limit: 8192 Token
- Fehler: 'the input length exceeds the context length'
- System crasht nach 10 Retries
Lösung:
1. Content für Embeddings auf 15.000 Zeichen kürzen (~4000 Token)
2. Trunk-Größe auf max 4000 begrenzt
3. Hinweis '[truncated for embedding]' bei Kürzung
Betroffene Dateien:
- rdagent/components/knowledge_management/vector_base.py
Jetzt sollte fin_quant ohne Embedding-Fehler durchlaufen.
* update all code
* update all code
* dump knowledge base
* rename the tag
* add timer to RD-Agent
* fix CI
* fix CI
* use batch embedding
* fix a small bug
* fix prompt bug
* feat: add pause resume to handle K8S cluster pause (#804)
* add resume to cluster running
* fix non-pickle problem
* fix a small bug
* fix a small bug
* avoid shutil move error
* refine the logic
* move knowledge base out of session
* avoid mistake information to pipeline coding
* avoid load and dump in steps
* archive the right folder
* small improvement
* avoid restart when timer is already started
* fix CI
---------
Co-authored-by: Xu Yang <xuyang1@microsoft.com>
---------
Co-authored-by: Xu Yang <peteryang@vip.qq.com>
Co-authored-by: Xu Yang <xuyang1@microsoft.com>
Co-authored-by: Xu <v-xuminrui@microsoft.com>
* several improvement on kaggle loop
* small refinement on prompt
* fix bugs
* add the score of each model in every experiment
* fix ci error
* fix error in ventilator tpl
* fix CI
---------
Co-authored-by: Xu Yang <xuyang1@microsoft.com>
Co-authored-by: Bowen Xian <xianbowen@outlook.com>
Co-authored-by: WinstonLiye <1957922024@qq.com>
Co-authored-by: TPLin22 <tplin2@163.com>
* ignore result csv file
* fix app scripts
* rename taskgenerator to developer and generate to develop
* fix a config bug in coder
* fix a small bug in factor coder evaluators
* remove a single logger in factor coder evaluators
* fix a small bug in model coder main.py
* rename Implementation to Workspace
* move the prepare the inject_code into FBWorkspace to align all the behavior
* fix a small bug in model feedback
* remove debug lines for multi processing and simplify evaluators multi proc
* add a copy function to workspace to freeze the workspace && add config prefix to speed up debugging
* make hypothesisgen a abc class
* use Qlib***Experiment
* fix a small bug
* rename Imp to Ws
* rename sub_implementations to sub_workspace_list
* fix a bug in feedback not presented as content in prompts
* move proposal pys to proposal folder
* reformat the folder
* align factor and model qlib workspace and use template to handle the workspace
* add a filter to evoagent to filter out false evo
* align multi_proc_n into RDAGENT seeting
* handle when runner gets empty experiment
* fix logger merge remaining problems
* fix black and isort automatically
* remove ruff comment in log.py
* change log framework and fix llm_utils.py's logs
* Some thoughts for logging
* fix SingletonMeta's definition, maintain an instance dict for each class that inherits it
* adjust log codes directory, add some tag for factor implementation logging
* Update rdagent/core/conf.py
* fix factor task app & log
* fix log import
* Streamlet framework
* fix log tag to path logic
* Add todos
* Add example in docstring
* add log tag for llm_utils.py
* Capture lost content
---------
Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
* Commit init framework
* Co-authored-by: Yuante Li (FESCO Adecco Human Resources) <v-yuanteli@microsoft.com>
Co-authored-by: XianBW <XianBW@users.noreply.github.com>
* add an import
* refine the whole framework
* benchmark related framework
* fix black and isort errors
* move requirements to folder
* fix black again
---------
Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: xuyang1 <xuyang1@microsoft.com>
TPTBusiness