Commit f90b0975 authored by Jan Reimes's avatar Jan Reimes
Browse files

📝 docs(ai): update documentation with new query and workspace features

parent 3f6a5eb1
Loading
Loading
Loading
Loading
+38 −38
Original line number Diff line number Diff line
@@ -97,6 +97,7 @@ The AI module follows a workspace-based workflow for organizing and querying you

```bash
#Create a new workspace for your project
tdoc-crawler ai workspace create my-project --auto-build
tdoc-crawler ai workspace create my-project
```

@@ -126,26 +127,16 @@ tdoc-crawler ai process --tdoc-id SP-240001 --checkout-path /path/to/checkout

### 4. Query Your Knowledge Base

Once processed, query your documents using semantic search or graph queries:
Once processed, query your documents using semantic search and knowledge graph (RAG + GraphRAG):

```bash
# Semantic search
tdoc-crawler ai query --workspace my-project --query "5G NR architecture" --top-k 5

# Knowledge graph query
tdoc-crawler ai graph --workspace my-project --query "evolution of 5G standards"
tdoc-crawler ai query --workspace my-project "your query here"
```

### 5. Check Status

Monitor processing status:
Once processed, query your documents using semantic search and knowledge graph (RAG + GraphRAG):

```bash
# Check status of specific TDoc
tdoc-crawler ai status --tdoc-id SP-240001

# List all processed documents
tdoc-crawler ai status --workspace my-project
tdoc-crawler ai query --workspace my-project "your query here"
```

______________________________________________________________________
@@ -156,7 +147,11 @@ ______________________________________________________________________

```bash
# Create a new workspace
tdoc-crawler ai workspace create <name>
tdoc-crawler ai workspace create <name> [--auto-build]

Options:
- `name`: Workspace name
- `--auto-build`: Automatically process documents when added to workspace

# List all workspaces
tdoc-crawler ai workspace list
@@ -168,42 +163,47 @@ tdoc-crawler ai workspace get <name>
tdoc-crawler ai workspace delete <name>
```

### Document Processing
### Querying

Query the knowledge graph using semantic embeddings and knowledge graph (RAG + GraphRAG).

```bash
# Process single TDoc
tdoc-crawler ai process --tdoc-id <TDOC_ID> --checkout-path <PATH>
tdoc-crawler ai query --workspace <workspace_name> "your query here"
```

# Process all TDocs in workspace
tdoc-crawler ai process-all --workspace <NAME>
Note: `--workspace` is required. This command uses both vector embeddings (RAG) and the knowledge graph (GraphRAG) to provide comprehensive results.

# Force re-processing
tdoc-crawler ai process --tdoc-id <TDOC_ID> --checkout-path <PATH> --force
```
### Single TDoc Operations

### Querying
#### Summarize a TDoc

```bash
# Semantic search
tdoc-crawler ai query --workspace <NAME> --query "<SEARCH_QUERY>" --top-k 5
Summarize a single TDoc with specified word count.

# Knowledge graph query
tdoc-crawler ai graph --workspace <NAME> --query "<GRAPH_QUERY>"
```bash
tdoc-crawler ai summarize <tdoc_id> [--words N] [--format markdown|json|yaml] [--json-output]
```

### Status
Options:

```bash
# Check processing status
tdoc-crawler ai status --tdoc-id <TDOC_ID>
- `tdoc_id`: TDoc identifier (e.g., "RP-240001")
- `--words N`: Target word count for summary (default: 200)
- `--format`: Output format - markdown (default), json, or yaml
- `--json-output`: Output raw JSON

# List all statuses in workspace
tdoc-crawler ai status --workspace <NAME>
#### Convert a TDoc

# Output as JSON
tdoc-crawler ai status --tdoc-id <TDOC_ID> --json
Convert a single TDoc to markdown format.

```bash
tdoc-crawler ai convert <tdoc_id> [--output FILE.md] [--json-output]
```

Options:

- `tdoc_id`: TDoc identifier
- `--output FILE.md`: Write output to file (prints to stdout if not specified)
- `--json-output`: Output raw JSON

______________________________________________________________________

## Model Providers