-
Notifications
You must be signed in to change notification settings - Fork 463
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
10 changed files
with
275 additions
and
34 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,19 @@ | ||
| import json | ||
|
|
||
| from superduper import Application, Document | ||
|
|
||
|
|
||
| def test_build_from_template(db): | ||
| from superduper import templates | ||
|
|
||
| db.apply(templates.simple_rag) | ||
|
|
||
| with open('test/material/sample_app/component.json') as f: | ||
| component = json.load(f) | ||
|
|
||
| component = templates.simple_rag.form_template | ||
| component['_variables']['output_prefix'] = '_output__' | ||
|
|
||
| c = Document.decode(component, db=db).unpack() | ||
|
|
||
| assert isinstance(c, Application) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,246 @@ | ||
| { | ||
| "_variables": { | ||
| "table_name": "sample_simple_rag", | ||
| "id_field": "_id", | ||
| "databackend": "mongodb", | ||
| "base_url": null, | ||
| "api_key": null, | ||
| "embedding_model": "text-embedding-ada-002", | ||
| "llm_model": "gpt-3.5-turbo" | ||
| }, | ||
| "types": { | ||
| "id_field": { | ||
| "type": "str", | ||
| "default": "_id" | ||
| }, | ||
| "embedding_model": { | ||
| "type": "str", | ||
| "default": "text-embedding-ada-002" | ||
| }, | ||
| "llm_model": { | ||
| "type": "str", | ||
| "default": "gpt-3.5-turbo" | ||
| }, | ||
| "table_name": { | ||
| "type": "str", | ||
| "default": "sample_simple_rag" | ||
| }, | ||
| "databackend": { | ||
| "type": "str", | ||
| "default": "mongodb" | ||
| }, | ||
| "base_url": { | ||
| "type": "str", | ||
| "optional": true, | ||
| "default": null | ||
| }, | ||
| "api_key": { | ||
| "type": "str", | ||
| "optional": true, | ||
| "default": null | ||
| } | ||
| }, | ||
| "_base": "?simple-rag-app", | ||
| "_builds": { | ||
| "datatype:dill": { | ||
| "_path": "superduper.components.datatype.get_serializer", | ||
| "method": "dill", | ||
| "encodable": "artifact" | ||
| }, | ||
| "727d3bb560939e1211f9cac189d56e07e9622eeb": { | ||
| "_path": "superduper.components.datatype.Artifact", | ||
| "datatype": "?datatype:dill", | ||
| "uri": null, | ||
| "blob": "&:blob:727d3bb560939e1211f9cac189d56e07e9622eeb" | ||
| }, | ||
| "model:chunker": { | ||
| "_object": "?727d3bb560939e1211f9cac189d56e07e9622eeb", | ||
| "upstream": null, | ||
| "plugins": null, | ||
| "cache": true, | ||
| "status": null, | ||
| "signature": "singleton", | ||
| "datatype": null, | ||
| "output_schema": null, | ||
| "model_update_kwargs": {}, | ||
| "predict_kwargs": {}, | ||
| "compute_kwargs": {}, | ||
| "validation": null, | ||
| "metric_values": {}, | ||
| "num_workers": 0, | ||
| "serve": false, | ||
| "trainer": null, | ||
| "deploy": false, | ||
| "chunk_size": 200 | ||
| }, | ||
| "var-table-name-select-var-id-field-x": { | ||
| "_path": "superduper_<var:databackend>.query.parse_query", | ||
| "documents": [], | ||
| "query": "<var:table_name>.select(\"<var:id_field>\", \"x\")" | ||
| }, | ||
| "listener:chunker": { | ||
| "_path": "superduper.components.listener.Listener", | ||
| "upstream": null, | ||
| "plugins": null, | ||
| "cache": true, | ||
| "status": null, | ||
| "cdc_table": "<var:table_name>", | ||
| "key": "x", | ||
| "model": "?model:chunker", | ||
| "predict_kwargs": {}, | ||
| "select": "?var-table-name-select-var-id-field-x", | ||
| "flatten": true | ||
| }, | ||
| "datatype:sqlvector[1536]": { | ||
| "_path": "superduper.components.vector_index.sqlvector", | ||
| "shape": [ | ||
| 1536 | ||
| ] | ||
| }, | ||
| "model:<var:embedding_model>": { | ||
| "_path": "superduper_openai.model.OpenAIEmbedding", | ||
| "upstream": null, | ||
| "plugins": null, | ||
| "cache": true, | ||
| "status": null, | ||
| "signature": "singleton", | ||
| "datatype": "?datatype:sqlvector[1536]", | ||
| "output_schema": null, | ||
| "model_update_kwargs": {}, | ||
| "predict_kwargs": {}, | ||
| "compute_kwargs": {}, | ||
| "validation": null, | ||
| "metric_values": {}, | ||
| "num_workers": 0, | ||
| "serve": false, | ||
| "trainer": null, | ||
| "deploy": false, | ||
| "model": "<var:embedding_model>", | ||
| "max_batch_size": 8, | ||
| "openai_api_key": null, | ||
| "openai_api_base": null, | ||
| "client_kwargs": { | ||
| "base_url": null, | ||
| "api_key": null | ||
| }, | ||
| "shape": [ | ||
| 1536 | ||
| ], | ||
| "batch_size": 100 | ||
| }, | ||
| "outputs-chunker-?(listener:chunker.uuid)-select-id-source-outputs-chunker-?(listener:chunker.uuid)": { | ||
| "_path": "superduper_<var:databackend>.query.parse_query", | ||
| "documents": [], | ||
| "query": "<var:output_prefix>chunker__?(listener:chunker.uuid).select(\"id\", \"_source\", \"<var:output_prefix>chunker__?(listener:chunker.uuid)\")" | ||
| }, | ||
| "listener:embeddinglistener": { | ||
| "_path": "superduper.components.listener.Listener", | ||
| "upstream": [ | ||
| "?listener:chunker", | ||
| "?listener:chunker" | ||
| ], | ||
| "plugins": null, | ||
| "cache": true, | ||
| "status": null, | ||
| "cdc_table": "<var:output_prefix>chunker__?(listener:chunker.uuid)", | ||
| "key": "<var:output_prefix>chunker__?(listener:chunker.uuid)", | ||
| "model": "?model:<var:embedding_model>", | ||
| "predict_kwargs": {}, | ||
| "select": "?outputs-chunker-?(listener:chunker.uuid)-select-id-source-outputs-chunker-?(listener:chunker.uuid)", | ||
| "flatten": false | ||
| }, | ||
| "vector_index:vectorindex": { | ||
| "_path": "superduper.components.vector_index.VectorIndex", | ||
| "upstream": null, | ||
| "plugins": null, | ||
| "cache": true, | ||
| "status": null, | ||
| "cdc_table": "<var:output_prefix>embeddinglistener__?(listener:embeddinglistener.uuid)", | ||
| "indexing_listener": "?listener:embeddinglistener", | ||
| "compatible_listener": null, | ||
| "measure": "cosine", | ||
| "metric_values": {} | ||
| }, | ||
| "outputs-chunker-?(listener:chunker.uuid)-select-like-outputs-chunker-?(listener:chunker.uuid)-var-query-vector-index-vectorindex-n-5": { | ||
| "_path": "superduper_<var:databackend>.query.parse_query", | ||
| "documents": [ | ||
| { | ||
| "<var:output_prefix>chunker__?(listener:chunker.uuid)": "<var:query>" | ||
| } | ||
| ], | ||
| "query": "<var:output_prefix>chunker__?(listener:chunker.uuid).select().like(documents[0], vector_index=\"vectorindex\", n=5)" | ||
| }, | ||
| "model:llm-model": { | ||
| "_path": "superduper_openai.model.OpenAIChatCompletion", | ||
| "upstream": null, | ||
| "plugins": null, | ||
| "cache": true, | ||
| "status": null, | ||
| "signature": "singleton", | ||
| "datatype": null, | ||
| "output_schema": null, | ||
| "model_update_kwargs": {}, | ||
| "predict_kwargs": {}, | ||
| "compute_kwargs": {}, | ||
| "validation": null, | ||
| "metric_values": {}, | ||
| "num_workers": 0, | ||
| "serve": false, | ||
| "trainer": null, | ||
| "deploy": false, | ||
| "model": "<var:llm_model>", | ||
| "max_batch_size": 8, | ||
| "openai_api_key": null, | ||
| "openai_api_base": null, | ||
| "client_kwargs": { | ||
| "base_url": null, | ||
| "api_key": null | ||
| }, | ||
| "batch_size": 1, | ||
| "prompt": "" | ||
| }, | ||
| "model:simple_rag": { | ||
| "_path": "superduper.components.model.RAGModel", | ||
| "upstream": null, | ||
| "plugins": null, | ||
| "cache": true, | ||
| "status": null, | ||
| "signature": "singleton", | ||
| "datatype": null, | ||
| "output_schema": null, | ||
| "model_update_kwargs": {}, | ||
| "predict_kwargs": {}, | ||
| "compute_kwargs": {}, | ||
| "validation": null, | ||
| "metric_values": {}, | ||
| "num_workers": 0, | ||
| "serve": false, | ||
| "trainer": null, | ||
| "deploy": false, | ||
| "prompt_template": "Use the following context snippets, these snippets are not ordered!, Answer the question based on this context.\nThese snippets are samples from our internal data-repositories, and should be used exclusively and as a matter of priority to answer the question\n\n{context}\n\nHere's the question: {query}", | ||
| "select": "?outputs-chunker-?(listener:chunker.uuid)-select-like-outputs-chunker-?(listener:chunker.uuid)-var-query-vector-index-vectorindex-n-5", | ||
| "key": "<var:output_prefix>chunker__?(listener:chunker.uuid)", | ||
| "llm": "?model:llm-model" | ||
| }, | ||
| "simple-rag-app": { | ||
| "_path": "superduper.components.application.Application", | ||
| "upstream": null, | ||
| "plugins": null, | ||
| "cache": true, | ||
| "status": null, | ||
| "components": [ | ||
| "?listener:chunker", | ||
| "?vector_index:vectorindex", | ||
| "?model:simple_rag" | ||
| ], | ||
| "namespace": null, | ||
| "link": null, | ||
| "_literals": [ | ||
| "template" | ||
| ] | ||
| } | ||
| }, | ||
| "_blobs": {}, | ||
| "_files": {}, | ||
| "_template_name": "simple_rag" | ||
| } |