phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 04:10:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

swapping to configuring the entire chunk template

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-05-13 22:47:35 -04:00
parent 2e70782e63
commit 66f7b42795
7 changed files with 58 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/source/building_applications/rag.md
View file

@ -99,14 +99,14 @@ results = client.tool_runtime.rag_tool.query(
)
```
You can configure adding metadata to the context if you find it useful for your application. Simply add:
You can configure how the RAG tool adds metadata to the context if you find it useful for your application. Simply add:
```python
# Query documents
results = client.tool_runtime.rag_tool.query(
vector_db_ids=[vector_db_id],
content="What do you know about...",
query_config={
"include_metadata_in_content": True,
"chunk_template": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
},
)
```
@ -131,7 +131,7 @@ agent = Agent(
"query_config": {
"chunk_size_in_tokens": 512,
"chunk_overlap_in_tokens": 0,
"include_metadata_in_content": False,
"chunk_template": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
},
},
}