|
|
7026fc4fed
|
Update components for WP-25b: Implement Lazy-Prompt-Orchestration across ingestion, decision engine, chat interface, and LLM service. Enhance prompt management with hierarchical model support and streamline response generation by removing manual formatting. Bump versions to reflect new features and optimizations.
|
2026-01-02 20:43:31 +01:00 |
|
|
|
9b906bbabf
|
Update FastAPI application and related services for WP-25a: Enhance lifespan management with Mixture of Experts (MoE) integrity checks, improve logging and error handling in LLMService, and integrate profile-driven orchestration across components. Bump versions for main application, ingestion services, and LLM profiles to reflect new features and optimizations.
|
2026-01-02 08:57:29 +01:00 |
|
|
|
d0eae8e43c
|
Update Decision Engine and related components for WP-25a: Bump version to 1.2.0, enhance multi-stream retrieval with pre-synthesis compression, and integrate Mixture of Experts (MoE) profile support. Refactor chat interface to utilize new compression logic and llm_profiles for improved synthesis. Maintain compatibility with existing methods and ensure robust error handling across services.
|
2026-01-02 07:04:43 +01:00 |
|
|
|
008167268f
|
Update main application and services for WP-25 release, introducing Agentic Multi-Stream RAG capabilities. Enhance lifespan management, global error handling, and integrate LLMService with DecisionEngine for improved retrieval and synthesis. Update dependencies and versioning across modules, ensuring compatibility with new multi-stream architecture. Refactor chat router to support new intent classification and retrieval strategies, while maintaining stability and performance improvements.
|
2026-01-01 07:52:41 +01:00 |
|
|
|
e93bab6ea7
|
Fassadenauflösung unter app/core
Deploy mindnet to llm-node / deploy (push) Successful in 4s
|
2025-12-28 11:04:40 +01:00 |
|
|
|
f686ecf947
|
anpassung an variable Kontextgrenzen für Ollama
Deploy mindnet to llm-node / deploy (push) Successful in 5s
|
2025-12-26 11:15:13 +01:00 |
|
|
|
cbaf664123
|
Die Context-Drossel (10.000 Zeichen), die Deaktivierung der Retry-Kaskaden (max_retries=0) für den Echtzeit-Chat und eine robustere Fehlerbehandlung für die LLM-Aufrufe.
Deploy mindnet to llm-node / deploy (push) Successful in 6s
|
2025-12-26 07:19:51 +01:00 |
|
|
|
43d3d8f7f3
|
debug für chat
Deploy mindnet to llm-node / deploy (push) Successful in 4s
|
2025-12-26 05:21:15 +01:00 |
|
|
|
83c0c9944d
|
angepasst an die neue LLM Logik
Deploy mindnet to llm-node / deploy (push) Successful in 4s
|
2025-12-26 05:11:48 +01:00 |
|
|
|
c9cf1b7e4c
|
WP20 - Chat Interface auf neue Struktur der decision.yaml
|
2025-12-25 11:50:08 +01:00 |
|
|
|
234949800b
|
WP20 initial
|
2025-12-23 14:33:51 +01:00 |
|
|
|
136c3bb43f
|
neue version
|
2025-12-18 14:00:08 +01:00 |
|
|
|
2c3ee8efd6
|
neu version
|
2025-12-18 13:56:45 +01:00 |
|
|
|
7f7d8c87db
|
neuer semantik retriever im Chat
|
2025-12-18 12:40:34 +01:00 |
|
|
|
6011b96fc1
|
neue ui Save-logik
|
2025-12-16 14:11:17 +01:00 |
|
|
|
7263fee4c7
|
prune
|
2025-12-15 17:55:53 +01:00 |
|
|
|
83bb18b6a7
|
code header
|
2025-12-15 15:40:39 +01:00 |
|
|
|
70ffa5cd4e
|
Frage wird durch ? oder Fragewort identifiziert
|
2025-12-12 21:56:17 +01:00 |
|
|
|
0b8f0a6c22
|
neue architekturaufteilung für chat in WP11 gebaut
|
2025-12-12 16:32:11 +01:00 |
|
|
|
52210a91fd
|
update aus WP11
|
2025-12-11 13:50:40 +01:00 |
|
|
|
f4299db347
|
WP10 Überarbeitung
|
2025-12-11 12:04:08 +01:00 |
|
|
|
06f77fe8b7
|
debug mode im router
|
2025-12-11 11:35:27 +01:00 |
|
|
|
fd47a954bd
|
bug fix
|
2025-12-11 11:11:01 +01:00 |
|
|
|
5aae33f578
|
bug fixing
|
2025-12-11 10:46:37 +01:00 |
|
|
|
a7cda3f51c
|
bugfix
|
2025-12-11 08:18:41 +01:00 |
|
|
|
565d34fb7b
|
Ergänzung und Korrektur
|
2025-12-10 22:17:40 +01:00 |
|
|
|
0170d9291f
|
erster Stand
|
2025-12-10 22:05:35 +01:00 |
|
|
|
86464cec11
|
erster Entwurf WP07
|
2025-12-10 13:48:13 +01:00 |
|
|
|
76ea8e3350
|
Update für Feedback Loop
|
2025-12-09 22:07:58 +01:00 |
|
|
|
2310633de3
|
payload durchreichen bis zum chat
|
2025-12-09 18:11:25 +01:00 |
|
|
|
bd36d78025
|
neue Test
|
2025-12-09 18:02:21 +01:00 |
|
|
|
6c2074166c
|
verbessertes Prompt, und chat-Router optimiert
|
2025-12-09 13:50:18 +01:00 |
|
|
|
bd44af2b68
|
korrektur zu besseren Analyse
|
2025-12-09 13:37:26 +01:00 |
|
|
|
03594424a1
|
Hybrider Chat (mit und ohne LLM Einordung des Intents)
|
2025-12-09 13:08:04 +01:00 |
|
|
|
97985371ca
|
neue engine mit mehreren typen
|
2025-12-09 09:58:35 +01:00 |
|
|
|
2fa24cb1bd
|
Konfiguierbare Entscheidungen
|
2025-12-08 19:36:12 +01:00 |
|
|
|
07b7f419de
|
Erste Version WP06
|
2025-12-08 18:48:24 +01:00 |
|
|
|
21904e62ee
|
go
|
2025-12-08 14:27:17 +01:00 |
|
|
|
531e3790b3
|
persönlichkeitsupdate
|
2025-12-08 13:39:16 +01:00 |
|
|
|
7745b71832
|
debug raus . aktualisierte chats
|
2025-12-08 11:15:16 +01:00 |
|
|
|
b39663408c
|
debug
|
2025-12-08 11:09:52 +01:00 |
|
|
|
90f0be6baf
|
erste Version WP05
|
2025-12-08 10:32:57 +01:00 |
|
|
|
caab41a760
|
WP04c
|
2025-12-07 19:29:48 +01:00 |
|
|
|
104ddddb96
|
app/routers/tools.py aktualisiert
Deploy mindnet to llm-node / deploy (push) Successful in 4s
|
2025-10-07 13:38:49 +02:00 |
|
|
|
c2ecc15d89
|
app/routers/tools.py aktualisiert
Deploy mindnet to llm-node / deploy (push) Successful in 3s
|
2025-10-07 13:30:12 +02:00 |
|
|
|
43e77c4c6b
|
app/routers/tools.py hinzugefügt
Deploy mindnet to llm-node / deploy (push) Successful in 3s
|
2025-10-07 13:19:48 +02:00 |
|
|
|
0f2f8208e3
|
app/routers/admin.py hinzugefügt
Deploy mindnet to llm-node / deploy (push) Successful in 3s
|
2025-10-07 11:32:12 +02:00 |
|
|
|
ba17516814
|
app/routers/graph.py hinzugefügt
Deploy mindnet to llm-node / deploy (push) Successful in 3s
|
2025-10-07 11:31:47 +02:00 |
|
|
|
c0979b69e2
|
app/routers/query.py hinzugefügt
Deploy mindnet to llm-node / deploy (push) Successful in 3s
|
2025-10-07 11:31:26 +02:00 |
|
|
|
e65ba23941
|
app/routers/qdrant_router.py aktualisiert
Deploy mindnet to llm-node / deploy (push) Successful in 3s
|
2025-09-02 17:05:36 +02:00 |
|
