Native CLI i18n: The TrustGraph CLI has built-in translation support that dynamically loads language strings. You can test and use different languages by simply passing the --lang flag (e.g., --lang es for Spanish, --lang ru for Russian) or by configuring your environment's LANG variable. Automated Docs Translations: This PR introduces autonomously translated Markdown documentation into several target languages, including Spanish, Swahili, Portuguese, Turkish, Hindi, Hebrew, Arabic, Simplified Chinese, and Russian.
4.6 KiB
| layout | title | parent |
|---|---|---|
| default | Pendekezo la Urekebishaji wa Saraka ya Mfumo | Swahili (Beta) |
Pendekezo la Urekebishaji wa Saraka ya Mfumo
Beta Translation: This document was translated via Machine Learning and as such may not be 100% accurate. All non-English languages are currently classified as Beta.
Masuala Yanayoendelea
- Muundo tambarare - Saraka moja inayokuwa na mifumo yote inafanya iwe ngumu kuelewa uhusiano.
- Mambo mchanganyikano - Aina za msingi, vitu vya kikoa, na mikatiba ya API yote yamechanganywa.
- Majina yasiyo wazi - Faili kama vile "object.py", "types.py", "topic.py" hazionyeshi wazi madhumuni yake.
- Hakuna tabaka wazi - Haiwezekani kuona kwa urahisi nini kinategemea nini.
Muundo Ulio Pendekezwa
trustgraph-base/trustgraph/schema/
├── __init__.py
├── core/ # Core primitive types used everywhere
│ ├── __init__.py
│ ├── primitives.py # Error, Value, Triple, Field, RowSchema
│ ├── metadata.py # Metadata record
│ └── topic.py # Topic utilities
│
├── knowledge/ # Knowledge domain models and extraction
│ ├── __init__.py
│ ├── graph.py # EntityContext, EntityEmbeddings, Triples
│ ├── document.py # Document, TextDocument, Chunk
│ ├── knowledge.py # Knowledge extraction types
│ ├── embeddings.py # All embedding-related types (moved from multiple files)
│ └── nlp.py # Definition, Topic, Relationship, Fact types
│
└── services/ # Service request/response contracts
├── __init__.py
├── llm.py # TextCompletion, Embeddings, Tool requests/responses
├── retrieval.py # GraphRAG, DocumentRAG queries/responses
├── query.py # GraphEmbeddingsRequest/Response, DocumentEmbeddingsRequest/Response
├── agent.py # Agent requests/responses
├── flow.py # Flow requests/responses
├── prompt.py # Prompt service requests/responses
├── config.py # Configuration service
├── library.py # Librarian service
└── lookup.py # Lookup service
Mabadiliko Muhimu
-
Mpangilio wa kimfumo - Tofauti wazi kati ya aina kuu, modeli za maarifa, na mikatiba ya huduma.
-
Majina bora zaidi:
types.py→core/primitives.py(lengo lililoboreshwa)object.py→ Kugawanywa katika faili zinazofaa kulingana na yaliyomo halisi.documents.py→knowledge/document.py(moja, thabiti)models.py→services/llm.py(wazi zaidi ni aina gani ya modeli)prompt.py→ Kugawanywa: sehemu za huduma hadiservices/prompt.py, aina za data hadiknowledge/nlp.py -
Punguzo la mantiki: Aina zote za kuingiza zimeunganishwa katika
knowledge/embeddings.pyMikatiba yote ya huduma inayohusiana na LLM iko katikaservices/llm.pyTofauti wazi ya jozi za ombi/jibu katika saraka ya huduma. Aina za utoaji wa maarifa zimepangwa pamoja na modeli zingine za uwanja wa maarifa. -
Ufafanuzi wa utegemezi: Aina kuu hazina utegemezi wowote. Modeli za maarifa hutegemea tu aina kuu. Mikatiba ya huduma inaweza kutegemea aina kuu na modeli za maarifa.
Faida za Uhamisho
- Uramaji rahisi - Wasanidi programu wanaweza kupata haraka kile wanachohitaji.
- Uunganishaji bora zaidi - Mipaka wazi kati ya masuala tofauti.
- Uingizaji rahisi zaidi - Njia za uingizaji ambazo ni za angavu zaidi.
- Inaweza kudumu kwa muda mrefu - Rahisi kuongeza aina mpya za maarifa au huduma bila kusumbua.
Mfano wa Mabadiliko ya Uingizaji
# Before
from trustgraph.schema import Error, Triple, GraphEmbeddings, TextCompletionRequest
# After
from trustgraph.schema.core import Error, Triple
from trustgraph.schema.knowledge import GraphEmbeddings
from trustgraph.schema.services import TextCompletionRequest
Maelezo ya Utendaji
- Hakikisha utangamano wa zamani kwa kudumisha uingizaji wa faili katika sehemu kuu
__init__.py - Hamisha faili hatua kwa hatua, na usasishe uingizaji wa faili kama inavyohitajika
- Fikiria kuongeza
legacy.pyambayo huingiza kila kitu kwa kipindi cha mpito - Sasisha nyaraka ili kuonyesha muundo mpya
<function_calls> [{"id": "1", "content": "Fanyia uchunguzi muundo wa sasa wa saraka ya schema", "status": "imekamilika", "priority": "juu"}, {"id": "2", "content": "Changanua faili za schema na madhumuni yao", "status": "imekamilika", "priority": "juu"}, {"id": "3", "content": "Pendekeza jina na muundo uliobora", "status": "imekamilika", "priority": "juu"}]