OpenAI Models
Works with v2.0+
This recipe demonstrates how to use OpenAI models in Spice.ai.
Prerequisites
Populate .env and Configure Spicepod
Populate .env with the following:
Verify that the spicepod.yaml is configured as follows:
datasets:
- from: github:github.com/spiceai/spiceai/files/trunk
name: spiceai.docs
description: Spice.ai project documentation (github.com/spiceai/spiceai)
params:
github_token: ${secrets:GITHUB_TOKEN}
include: "docs/**/*.md"
file_format: md
acceleration:
enabled: true
engine: cayenne
columns:
- name: content
embeddings:
- from: embeddings-model
row_id:
- path
chunking:
enabled: true
target_chunk_size: 256
overlap_size: 64
embeddings:
- from: openai:text-embedding-3-small
name: embeddings-model
params:
openai_api_key: ${secrets:OPENAI_API_KEY}
models:
- from: openai:gpt-6-luna
name: chat-model
params:
# gpt-6-luna accepts function tools on chat completions only with reasoning_effort none.
reasoning_effort: none
openai_api_key: ${secrets:OPENAI_API_KEY}
tools: auto
system_prompt: |
You are a helpful Spice.ai Docs assistant.
datasets:
- from: github:github.com/spiceai/spiceai/files/trunk
name: spiceai.docs
description: Spice.ai project documentation (github.com/spiceai/spiceai)
params:
github_token: ${secrets:GITHUB_TOKEN}
include: "docs/**/*.md"
file_format: md
acceleration:
enabled: true
engine: cayenne
columns:
- name: content
embeddings:
- from: embeddings-model
row_id:
- path
chunking:
enabled: true
target_chunk_size: 256
overlap_size: 64
embeddings:
- from: openai:text-embedding-3-small
name: embeddings-model
params:
openai_api_key: ${secrets:OPENAI_API_KEY}
models:
- from: openai:gpt-6-luna
name: chat-model
params:
# gpt-6-luna accepts function tools on chat completions only with reasoning_effort none.
reasoning_effort: none
openai_api_key: ${secrets:OPENAI_API_KEY}
tools: auto
system_prompt: |
You are a helpful Spice.ai Docs assistant.
Run Spice
Result:
INFO Spice.ai runtime starting...
2025-01-20T16:19:45.057495Z INFO runtime::http: Spice Runtime HTTP listening on 127.0.0.1:8090
2025-01-20T16:19:45.057562Z INFO runtime::flight: Spice Runtime Flight listening on 127.0.0.1:50051
2025-01-20T16:19:45.544466Z INFO runtime::init::embedding: Embedding Model embeddings-model ready
2025-01-20T16:19:45.544649Z INFO runtime::init::dataset: Dataset spiceai.docs initializing...
2025-01-20T16:19:45.544669Z INFO runtime::init::caching: Initialized sql results cache; max size: 128.00 MiB, item ttl: 1s, hashing algorithm: XXH3, encoding: none
2025-01-20T16:19:45.544761Z INFO runtime::init::model: Loading model [chat-model] from openai:gpt-6-luna...
2025-01-20T16:19:46.164600Z INFO runtime::init::dataset: Dataset spiceai.docs registered (github:github.com/spiceai/spiceai/files/trunk), acceleration (cayenne), results cache enabled.
2025-01-20T16:19:46.165929Z INFO runtime_table::accelerated::refresh_task: Loading data for dataset spiceai.docs
2025-01-20T16:19:46.534044Z INFO runtime::init::model: Model [chat-model] deployed, ready for inferencing
2025-01-20T16:19:49.394003Z INFO runtime_table::accelerated::refresh_task: Loaded 93 rows (1.28 MiB) for dataset spiceai.docs in 3s 228ms.
INFO Spice.ai runtime starting...
2025-01-20T16:19:45.057495Z INFO runtime::http: Spice Runtime HTTP listening on 127.0.0.1:8090
2025-01-20T16:19:45.057562Z INFO runtime::flight: Spice Runtime Flight listening on 127.0.0.1:50051
2025-01-20T16:19:45.544466Z INFO runtime::init::embedding: Embedding Model embeddings-model ready
2025-01-20T16:19:45.544649Z INFO runtime::init::dataset: Dataset spiceai.docs initializing...
2025-01-20T16:19:45.544669Z INFO runtime::init::caching: Initialized sql results cache; max size: 128.00 MiB, item ttl: 1s, hashing algorithm: XXH3, encoding: none
2025-01-20T16:19:45.544761Z INFO runtime::init::model: Loading model [chat-model] from openai:gpt-6-luna...
2025-01-20T16:19:46.164600Z INFO runtime::init::dataset: Dataset spiceai.docs registered (github:github.com/spiceai/spiceai/files/trunk), acceleration (cayenne), results cache enabled.
2025-01-20T16:19:46.165929Z INFO runtime_table::accelerated::refresh_task: Loading data for dataset spiceai.docs
2025-01-20T16:19:46.534044Z INFO runtime::init::model: Model [chat-model] deployed, ready for inferencing
2025-01-20T16:19:49.394003Z INFO runtime_table::accelerated::refresh_task: Loaded 93 rows (1.28 MiB) for dataset spiceai.docs in 3s 228ms.
At startup the runtime logs WARN runtime_parameters: Ignoring parameter 'file_format': not supported for connector github. — this is expected and
harmless. The GitHub connector has no file_format parameter, but the chunker
reads the dataset's file_format directly and uses it to pick the Markdown-aware
splitter, which is what the setting is for here. Removing it falls back to the
plain text splitter.
SQL Search
- Execute a Basic SQL Query to perform keyword searches within the dataset:
Then:
SELECT path
FROM spiceai.docs
WHERE
LOWER(content) LIKE '%errors%'
AND NOT contains(path, 'docs/release_notes');
SELECT path
FROM spiceai.docs
WHERE
LOWER(content) LIKE '%errors%'
AND NOT contains(path, 'docs/release_notes');
Result:
+------------------------------+
| path |
+------------------------------+
| docs/criteria/definitions.md |
| docs/dev/error_handling.md |
| docs/dev/metrics.md |
| docs/dev/style_guide.md |
+------------------------------+
Time: 0.006798 seconds. 4 rows.
+------------------------------+
| path |
+------------------------------+
| docs/criteria/definitions.md |
| docs/dev/error_handling.md |
| docs/dev/metrics.md |
| docs/dev/style_guide.md |
+------------------------------+
Time: 0.006798 seconds. 4 rows.
Utilizing Vector-Based Search
curl -XPOST http://localhost:8090/v1/search \
-H "Content-Type: application/json" \
-d "{
\"datasets\": [\"spiceai.docs\"],
\"text\": \"TEL metrics naming\",
\"where\": \"not contains(path, 'docs/release_notes')\",
\"additional_columns\": [\"download_url\"],
\"limit\": 2
}"
curl -XPOST http://localhost:8090/v1/search \
-H "Content-Type: application/json" \
-d "{
\"datasets\": [\"spiceai.docs\"],
\"text\": \"TEL metrics naming\",
\"where\": \"not contains(path, 'docs/release_notes')\",
\"additional_columns\": [\"download_url\"],
\"limit\": 2
}"
Result
{
"results": [
{
"matches": {
"content": [
"# Metrics Naming\n\n## TL;DR\n\n**Metric Naming Guide**: Prioritize Developer Experience (DX) with intuitive, ..."
]
},
"_score": 0.7941223368131454,
"dataset": "spiceai.docs",
"data": {
"download_url": "https://raw.githubusercontent.com/spiceai/spiceai/trunk/docs/dev/metrics.md"
}
},
{
"matches": {
"content": [
"# Criteria Definitions\n\n## RC\n\nAcronym for \"Release Candidate\". Identifies a version that is eligible for ..."
]
},
"_score": 0.7145749783070606,
"dataset": "spiceai.docs",
"data": {
"download_url": "https://raw.githubusercontent.com/spiceai/spiceai/trunk/docs/criteria/definitions.md"
}
}
],
"duration_ms": 745
}
{
"results": [
{
"matches": {
"content": [
"# Metrics Naming\n\n## TL;DR\n\n**Metric Naming Guide**: Prioritize Developer Experience (DX) with intuitive, ..."
]
},
"_score": 0.7941223368131454,
"dataset": "spiceai.docs",
"data": {
"download_url": "https://raw.githubusercontent.com/spiceai/spiceai/trunk/docs/dev/metrics.md"
}
},
{
"matches": {
"content": [
"# Criteria Definitions\n\n## RC\n\nAcronym for \"Release Candidate\". Identifies a version that is eligible for ..."
]
},
"_score": 0.7145749783070606,
"dataset": "spiceai.docs",
"data": {
"download_url": "https://raw.githubusercontent.com/spiceai/spiceai/trunk/docs/criteria/definitions.md"
}
}
],
"duration_ms": 745
}
Version note: The relevance score is returned in the _score field (leading underscore) on Spice v2.0+. On v1.x it was returned as score (no underscore).
Utilizing a natural language query
Use spice chat CLI command to query information using natural language
spice chat
Using model: chat-model
spice chat
Using model: chat-model
Perform test queries:
chat> what datasets you have access to
I have access to the following dataset:
- **Dataset Name:** spice.spiceai.docs
- **Description:** Spice.ai project documentation (github.com/spiceai/spiceai)
- **Can Search Documents:** Yes
This dataset contains documentation related to the Spice.ai project.
chat> what datasets you have access to
I have access to the following dataset:
- **Dataset Name:** spice.spiceai.docs
- **Description:** Spice.ai project documentation (github.com/spiceai/spiceai)
- **Can Search Documents:** Yes
This dataset contains documentation related to the Spice.ai project.
chat> What are release criterias?
The release criteria for Spice.ai components, such as models, data accelerators, and catalog connectors, are divided into stages, including Release Candidate (RC) and Stable release criteria. Here are the details for RC Criteria:
### RC Release Criteria
- **Beta Criteria**: All beta release criteria must pass.
- **Performance and Latency**: The model or component must handle consistent requests from several clients without adverse impacts on latency.
- Example: 8 clients sending consistent requests for 60 minutes.
...
chat> What are release criterias?
The release criteria for Spice.ai components, such as models, data accelerators, and catalog connectors, are divided into stages, including Release Candidate (RC) and Stable release criteria. Here are the details for RC Criteria:
### RC Release Criteria
- **Beta Criteria**: All beta release criteria must pass.
- **Performance and Latency**: The model or component must handle consistent requests from several clients without adverse impacts on latency.
- Example: 8 clients sending consistent requests for 60 minutes.
...
![dependabot[bot]](https://avatars.githubusercontent.com/in/29110?v=4)
