Skip to content

Commit 8808be6

Browse files
committed
docs(readme): add task-specific model examples to Getting Started sections
1 parent 86e33fc commit 8808be6

File tree

1 file changed

+6
-6
lines changed

1 file changed

+6
-6
lines changed

README.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -25,15 +25,13 @@ sqlite3 myapp.db
2525
```sql
2626
-- Load the extension
2727
.load ./ai
28-
29-
-- Load a GGUF model
30-
SELECT llm_model_load('./models/llama.gguf', 'gpu_layers=99');
3128
```
3229

3330
### Text Generation
3431

3532
```sql
36-
-- Create a text generation context
33+
-- Load a text generation model
34+
SELECT llm_model_load('./models/Qwen2.5-3B-Q4_K_M.gguf', 'gpu_layers=99');
3735
SELECT llm_context_create_textgen();
3836

3937
-- Generate text
@@ -43,7 +41,8 @@ SELECT llm_text_generate('What is the most beautiful city in Italy?');
4341
### Embedding Generation
4442

4543
```sql
46-
-- Create an embedding context
44+
-- Load an embedding model
45+
SELECT llm_model_load('./models/nomic-embed-text-v1.5-Q8_0.gguf', 'gpu_layers=99');
4746
SELECT llm_context_create_embedding('embedding_type=FLOAT32');
4847

4948
-- Generate an embedding vector
@@ -56,7 +55,8 @@ SELECT llm_embed_generate('Hello world', 'json_output=1');
5655
### Chat
5756

5857
```sql
59-
-- Create a chat context
58+
-- Load a chat model
59+
SELECT llm_model_load('./models/Llama-3.2-3B-Instruct-Q4_K_M.gguf', 'gpu_layers=99');
6060
SELECT llm_context_create_chat();
6161

6262
-- Send a message and get a complete response

0 commit comments

Comments
 (0)