Commit 2f6d4695 authored by Jan Reimes's avatar Jan Reimes
Browse files

docs: fix AI workflow documentation - remove non-existent checkout --workspace option

parent 37cfe8bd
Loading
Loading
Loading
Loading
+19 −36
Original line number Diff line number Diff line
@@ -101,44 +101,30 @@ tdoc-crawler ai workspace create my-project --auto-build
tdoc-crawler ai workspace create my-project
```

### 2. Add Documents to Workspace
### 2. Query Your Knowledge Base

Use the existing `checkout` and `checkout-spec` commands to download documents:
Once you have a workspace with documents, query using semantic search and knowledge graph (RAG + GraphRAG):

```bash
# Add TDocs to workspace
tdoc-crawler checkout --workspace my-project SP-240001 SP-240002

# Add specifications
tdoc-crawler checkout-spec --workspace my-project 23.501 23.502
tdoc-crawler ai query --workspace my-project "your query here"
```

### 3. Process Documents (Build Knowledge Base)

Process documents to extract content, generate embeddings, and create summaries:

```bash
# Process all documents in workspace
tdoc-crawler ai process-all --workspace my-project

# Or process individual TDoc
tdoc-crawler ai process --tdoc-id SP-240001 --checkout-path /path/to/checkout
```
Note: `--workspace` is required. This command uses both vector embeddings (RAG) and the knowledge graph (GraphRAG) to provide comprehensive results.

### 4. Query Your Knowledge Base
### 3. Single TDoc Operations

Once processed, query your documents using semantic search and knowledge graph (RAG + GraphRAG):
For individual TDocs, use the `summarize` and `convert` commands:

```bash
tdoc-crawler ai query --workspace my-project "your query here"
```
# Summarize a TDoc
tdoc-crawler ai summarize S4-251971 --words 200 --format markdown

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

```bash
tdoc-crawler ai query --workspace my-project "your query here"
# Convert a TDoc to markdown
tdoc-crawler ai convert S4-251971 --output S4-251971.md
```

Note: These commands work directly on TDoc IDs and do not require a workspace. They fetch metadata and content from configured sources.

______________________________________________________________________

## CLI Commands
@@ -434,24 +420,21 @@ ollama pull embeddinggemma
tdoc-crawler ai workspace create my-project
```

**Problem:** `No documents found in workspace`

**Solution:** Add documents to the workspace using `checkout` or `checkout-spec` commands, then process them:
**Solution:** Use `ai summarize` or `ai convert` to work with individual TDocs directly. These commands fetch content from configured sources:

```bash
tdoc-crawler checkout --workspace my-project SP-240001
tdoc-crawler ai process-all --workspace my-project
tdoc-crawler ai summarize SP-240001
tdoc-crawler ai convert SP-240001 --output SP-240001.md
```

### Processing Errors
### Query Errors

**Problem:** `TDoc 'SP-240001' not found in checkout path`
**Problem:** `TDoc 'SP-240001' not found`

**Solution:** Ensure the TDoc has been downloaded to the specified path:
**Solution:** Ensure the TDoc exists in your workspace or use `ai summarize`/`ai convert` which fetch from external sources:

```bash
tdoc-crawler checkout SP-240001
tdoc-crawler ai process --tdoc-id SP-240001 --checkout-path ~/.tdoc-crawler/checkout
tdoc-crawler ai summarize SP-240001 --format markdown
```

**Problem:** `LLM API timeout`