Coding an AutoAI RAG experiment with a Chroma vector store
Last updated: Feb 21, 2025
Coding an AutoAI RAG experiment with a Chroma vector store
Review the guidelines and code samples to learn how to code an AutoAI RAG experiment using the default, in-memory Chroma database as a vector store.
Storing vectorized content in a Chroma database
Copy link to section
When you set up your AutoAI RAG experiment and don't specify a connection to a vector store, the vectorized content is saved to the default, in-memory Chroma database. The content does not persist beyond the experiment, so this is not a viable
production method for deploying a RAG pattern. However, it provides a fastpath for creating a RAG pattern.
input_data_references supports up to 20 DataConnection instances.
Evaluation data
Copy link to section
Evaluation data must be in JSON format with a fixed schema with these fields: question, correct_answer, correct_answer_document_ids
For example:
[
{
"question": "What is the purpose of get_token()?",
"correct_answer": "get_token() is used to retrieve an authentication token for secure API access.",
"correct_answer_document_ids": [
"core_api.html"
]
},
{
"question": "How does the delete_model() function operate?",
"correct_answer": "delete_model() method allows users to delete models they've created or managed.",
"correct_answer_document_ids": [
"core_api.html"
]
}
]
The rag_optimizer object provides a set of methods for working with the AutoAI RAG experiment. In this step, enter the details to define the experiment. These are the available configuration options:
Run the optimizer to create the RAG patterns using the specified configuration options. In this code sample for running a Chroma experiment, the task is run in interactive mode. You can run the task in the background by changing the background_mode to True.
Step 4: Review the patterns and select the best one
Copy link to section
After the AutoAI RAG experiment completes successfully, you can review the patterns. Use the summary method to list completed patterns and evaluation metrics information in the form of a Pandas DataFrame so you can review the patterns,
ranked according to performance against the optimized metric.
summary = rag_optimizer.summary()
summary
Copy to clipboardCopied to clipboard
For example, pattern results display like this:
Pattern
mean_answer_correctness
mean_faithfulness
mean_context_correctness
chunking.chunk_size
embeddings.model_id
vector_store.distance_metric
retrieval.method
retrieval.number_of_chunks
generation.model_id
Pattern1
0.6802
0.5407
1.0000
512
ibm/slate-125m-english-rtrvr
euclidean
window
5
meta-llama/llama-3-70b-instruct
Pattern2
0.7172
0.5950
1.0000
1024
intfloat/multilingual-e5-large
euclidean
window
5
ibm/granite-13b-chat-v2
Pattern3
0.6543
0.5144
1.0000
1024
intfloat/multilingual-e5-large
euclidean
simple
5
ibm/granite-13b-chat-v2
Pattern4
0.6216
0.5030
1.0000
1024
intfloat/multilingual-e5-large
cosine
window
5
meta-llama/llama-3-70b-instruct
Pattern5
0.7369
0.5630
1.0000
1024
intfloat/multilingual-e5-large
cosine
window
3
mistralai/mixtral-8x7b-instruct-v01
Select a pattern to test locally
Copy link to section
The next step is select a pattern and test it locally. Because Chroma is in-memory, you must recreate the document index.
Tip:
In the following code sample, the index is built with the documents core_api.html and fm_embeddings.html.
payload = {
client.deployments.ScoringMetaNames.INPUT_DATA: [
{
"values": ["How to use new approach of providing credentials to APIClient?"],
}
]
}
best_pattern.query(payload)
Copy to clipboardCopied to clipboard
The model's response looks like this:
According to the document, the new approach to provide credentials to APIClient is by using the Credentials class. Here's an example:
from ibm_watsonx_ai import APIClient
from ibm_watsonx_ai import Credentials
credentials = Credentials(
url = "https://us-south.ml.cloud.ibm.com",
token = "***********",
)
client = APIClient(credentials)
This replaces the old approach of passing a dictionary with credentials to the APIClient constructor.
Copy to clipboardCopied to clipboard
Tip:
To retrieve a specific pattern, pass the pattern number to rag_optimizer.get_pattern().
Reviewing experiment results in Cloud Object Storage
Copy link to section
If the final status of the experiment is failed or error, use rag_optimizer.get_logs() or refer to experiment results to understand what went wrong. Experiment results and logs are stored in the default Cloud Object Storage instance
linked to your account. By default, results are saved in the default_autoai_rag_out directory.
The evaluation_results.json file contains evaluation results for each benchmark question.
The indexing_inference_notebook.ipynb contains the python code for building vector database index as well as building retrieval and generation function. The notebook introduces commands for retrieving data, chunking, and embeddings
creation as well as for retrieving chunks, building prompts and generating answers.
Note:
The results notebook indexing_notebook.ipynb contains the code for embedding and indexing the documents. You can accelerate the document indexing task by changing vector_store.add_documents() to vector_store.add_documents_async().
Get inference and indexing notebook
Copy link to section
To download a specified inference notebook, use the get_inference_notebook(). If you leave pattern_name empty, the method downloads the notebook of the best computed pattern.