Skip to content

Commit 388ea35

Browse files
tisniktisnik
authored
Merge pull request #1841 from tisnik/lcore-2086-reformat-tables
LCORE-2086: Reformat tables
2 parents 4b8f2c8 + c353c28 commit 388ea35

5 files changed

Lines changed: 371 additions & 371 deletions

File tree

‎docs/ARCHITECTURE.md‎

Lines changed: 15 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@ To enhance LLM responses, LCore leverages **RAG (Retrieval-Augmented Generation)
4444
```
4545
┌─────────────────────────────────────────────────────────┐
4646
│ Client Applications │
47-
│ (Web UI, CLI, VS Code Extension, Mobile Apps, etc.) │
47+
│ (Web UI, CLI, VS Code Extension, Mobile Apps, etc.) │
4848
└────────────────────┬────────────────────────────────────┘
4949
│ REST/A2A/JSON-RPC
5050
▼
@@ -150,14 +150,14 @@ LCore requires two main configuration files:
150150

151151
**Authentication Providers:**
152152

153-
| Provider | Use Case | Token Handling |
154-
|----------|----------|----------------|
155-
| **No Auth** | Development, testing | No token (empty string) |
156-
| **No Auth + Token** | Testing with token passthrough | Bearer token passed through |
157-
| **Kubernetes** | K8s service accounts | K8s service account token validated and forwarded |
158-
| **Red Hat SSO** | Red Hat environments | X-RH-Identity header (no separate token) |
159-
| **API Key** | API key authentication | API key from Authorization header |
160-
| **JWK/JWT** | JWT tokens | JWT validated and forwarded |
153+
| Provider | Use Case | Token Handling |
154+
|---------------------|--------------------------------|---------------------------------------------------|
155+
| **No Auth** | Development, testing | No token (empty string) |
156+
| **No Auth + Token** | Testing with token passthrough | Bearer token passed through |
157+
| **Kubernetes** | K8s service accounts | K8s service account token validated and forwarded |
158+
| **Red Hat SSO** | Red Hat environments | X-RH-Identity header (no separate token) |
159+
| **API Key** | API key authentication | API key from Authorization header |
160+
| **JWK/JWT** | JWT tokens | JWT validated and forwarded |
161161

162162
**Authentication Result (AuthTuple):**
163163

@@ -427,12 +427,12 @@ LCore uses a multi-database strategy to optimize for different data access patte
427427

428428
The system uses **4 separate databases** for different purposes:
429429

430-
| Database | Purpose | Technology | Size |
431-
|----------|---------|------------|------|
432-
| **User DB** | Conversation metadata | SQLAlchemy ORM | Small |
433-
| **Cache DB** | Full conversation transcripts | psycopg2/sqlite3 | Large |
434-
| **Quota DB** | Token usage and limits | psycopg2/sqlite3 | Medium |
435-
| **A2A DB** | Agent-to-agent protocol state | SQLAlchemy async | Small |
430+
| Database | Purpose | Technology | Size |
431+
|--------------|-------------------------------|------------------|--------|
432+
| **User DB** | Conversation metadata | SQLAlchemy ORM | Small |
433+
| **Cache DB** | Full conversation transcripts | psycopg2/sqlite3 | Large |
434+
| **Quota DB** | Token usage and limits | psycopg2/sqlite3 | Medium |
435+
| **A2A DB** | Agent-to-agent protocol state | SQLAlchemy async | Small |
436436

437437
### 4.2 Why Separate Databases?
438438

‎docs/a2a_protocol.md‎

Lines changed: 11 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -354,14 +354,14 @@ A2A Request
354354

355355
### Task States
356356

357-
| State | Description |
358-
|-------|-------------|
359-
| `submitted` | Task has been received and queued |
360-
| `working` | Task is being processed |
361-
| `completed` | Task finished successfully |
362-
| `failed` | Task failed with an error |
357+
| State | Description |
358+
|------------------|--------------------------------------------|
359+
| `submitted` | Task has been received and queued |
360+
| `working` | Task is being processed |
361+
| `completed` | Task finished successfully |
362+
| `failed` | Task failed with an error |
363363
| `input_required` | Agent needs additional input from the user |
364-
| `auth_required` | Authentication is required to continue |
364+
| `auth_required` | Authentication is required to continue |
365365

366366
### Multi-Turn Conversations
367367

@@ -527,10 +527,10 @@ curl -X POST http://localhost:8090/a2a \
527527

528528
A2A messages support an optional `metadata` field that can be used to pass additional parameters to control request routing and behavior. The following metadata fields are supported:
529529

530-
| Field | Type | Description |
531-
|-------|------|-------------|
532-
| `model` | `string` | Specify the LLM model to use for this request (e.g., `"gpt-4"`, `"llama3.1"`) |
533-
| `provider` | `string` | Specify the LLM provider to use (e.g., `"openai"`, `"watsonx"`) |
530+
| Field | Type | Description |
531+
|--------------------|----------------|--------------------------------------------------------------------------------------------------------|
532+
| `model` | `string` | Specify the LLM model to use for this request (e.g., `"gpt-4"`, `"llama3.1"`) |
533+
| `provider` | `string` | Specify the LLM provider to use (e.g., `"openai"`, `"watsonx"`) |
534534
| `vector_store_ids` | `list[string]` | Specify which vector stores to query for RAG. If not provided, all available vector stores are queried |
535535

536536
#### Example: Using Metadata

‎docs/byok_guide.md‎

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -191,15 +191,15 @@ byok_rag:
191191
192192
**`byok_rag` field reference:**
193193

194-
| Field | Required | Default | Description |
195-
|-------|----------|---------|-------------|
196-
| `rag_id` | Yes | — | Unique identifier for the knowledge source |
197-
| `rag_type` | No | `inline::faiss` | Vector store provider type |
198-
| `embedding_model` | No | `sentence-transformers/all-mpnet-base-v2` | Embedding model identifier or path |
199-
| `embedding_dimension` | No | `768` | Embedding vector dimensionality |
200-
| `vector_db_id` | Yes | — | Vector store ID generated by rag-content (e.g. `vs_8c94967b-81cc-4028-a294-9cfac6fd9ae2`) |
201-
| `db_path` | Yes | — | Path to the vector database file |
202-
| `score_multiplier` | No | `1.0` | Weight for Inline RAG ranking (values > 1.0 boost; < 1.0 reduce) |
194+
| Field | Required | Default | Description |
195+
|-----------------------|----------|-------------------------------------------|-------------------------------------------------------------------------------------------|
196+
| `rag_id` | Yes | — | Unique identifier for the knowledge source |
197+
| `rag_type` | No | `inline::faiss` | Vector store provider type |
198+
| `embedding_model` | No | `sentence-transformers/all-mpnet-base-v2` | Embedding model identifier or path |
199+
| `embedding_dimension` | No | `768` | Embedding vector dimensionality |
200+
| `vector_db_id` | Yes | — | Vector store ID generated by rag-content (e.g. `vs_8c94967b-81cc-4028-a294-9cfac6fd9ae2`) |
201+
| `db_path` | Yes | — | Path to the vector database file |
202+
| `score_multiplier` | No | `1.0` | Weight for Inline RAG ranking (values > 1.0 boost; < 1.0 reduce) |
203203

204204
**Multiple knowledge sources:**
205205

@@ -251,10 +251,10 @@ okp:
251251

252252
Both modes can be enabled simultaneously. Choose based on your latency and control preferences:
253253

254-
| Mode | When context is fetched | Tool call needed | score_multiplier |
255-
|------|------------------------|------------------|-----------------|
256-
| Inline RAG | With every query | No | Yes (BYOK only) |
257-
| Tool RAG | On LLM demand | Yes | No |
254+
| Mode | When context is fetched | Tool call needed | score_multiplier |
255+
|------------|-------------------------|------------------|------------------|
256+
| Inline RAG | With every query | No | Yes (BYOK only) |
257+
| Tool RAG | On LLM demand | Yes | No |
258258

259259
> [!TIP]
260260
> A ready-to-use example combining BYOK and OKP is available at

0 commit comments

Comments
 (0)