-
Notifications
You must be signed in to change notification settings - Fork 2.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
community[minor]: feat: QdrantTranslator for self-query retrieval (#5163
) * feat: Qdrant self-query retriever * docs: Qdrant self-query retriever * Update lock, fix type * Fix deps * Move to community * Revert * Move * Bump dep --------- Co-authored-by: jacoblee93 <[email protected]>
- Loading branch information
1 parent
dd7f528
commit 916114b
Showing
10 changed files
with
837 additions
and
17 deletions.
There are no files selected for viewing
53 changes: 53 additions & 0 deletions
53
...e_docs/docs/modules/data_connection/retrievers/self_query/qdrant-self-query.mdx
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 +1,53 @@ | ||
| # Qdrant Self Query Retriever | ||
|
|
||
| This example shows how to use a self query retriever with a Qdrant vector store. | ||
|
|
||
| ## Usage | ||
|
|
||
| import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx"; | ||
|
|
||
| <IntegrationInstallTooltip></IntegrationInstallTooltip> | ||
|
|
||
| ```bash npm2yarn | ||
| npm install @langchain/openai @langchain/community @qdrant/js-client-rest | ||
| ``` | ||
|
|
||
| import CodeBlock from "@theme/CodeBlock"; | ||
| import Example from "@examples/retrievers/qdrant_self_query.ts"; | ||
|
|
||
| <CodeBlock language="typescript">{Example}</CodeBlock> | ||
|
|
||
| You can also initialize the retriever with default search parameters that apply in | ||
| addition to the generated query: | ||
|
|
||
| ```typescript | ||
| const selfQueryRetriever = SelfQueryRetriever.fromLLM({ | ||
| llm, | ||
| vectorStore, | ||
| documentContents, | ||
| attributeInfo, | ||
| /** | ||
| * We need to create a basic translator that translates the queries into a | ||
| * filter format that the vector store can understand. We provide a basic translator here. | ||
| * You can create your own translator by extending BaseTranslator | ||
| * abstract class. Note that the vector store needs to support filtering on the metadata | ||
| * attributes you want to query on. | ||
| */ | ||
| structuredQueryTranslator: new QdrantTranslator(), | ||
| searchParams: { | ||
| filter: { | ||
| must: [ | ||
| { | ||
| key: "metadata.rating", | ||
| range: { | ||
| gt: 8.5, | ||
| }, | ||
| }, | ||
| ], | ||
| }, | ||
| mergeFiltersOperator: "and", | ||
| }, | ||
| }); | ||
| ``` | ||
|
|
||
| See the [official docs](https://qdrant.tech/documentation/concepts/filtering/) for more on how to construct metadata filters. |
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 +1,134 @@ | ||
| import { AttributeInfo } from "langchain/schema/query_constructor"; | ||
| import { OpenAIEmbeddings, OpenAI } from "@langchain/openai"; | ||
| import { SelfQueryRetriever } from "langchain/retrievers/self_query"; | ||
| import { QdrantVectorStore } from "@langchain/community/vectorstores/qdrant"; | ||
| import { QdrantTranslator } from "@langchain/community/retrievers/self_query/qdrant"; | ||
| import { Document } from "@langchain/core/documents"; | ||
|
|
||
| import { QdrantClient } from "@qdrant/js-client-rest"; | ||
|
|
||
| /** | ||
| * First, we create a bunch of documents. You can load your own documents here instead. | ||
| * Each document has a pageContent and a metadata field. Make sure your metadata matches the AttributeInfo below. | ||
| */ | ||
| const docs = [ | ||
| new Document({ | ||
| pageContent: | ||
| "A bunch of scientists bring back dinosaurs and mayhem breaks loose", | ||
| metadata: { year: 1993, rating: 7.7, genre: "science fiction" }, | ||
| }), | ||
| new Document({ | ||
| pageContent: | ||
| "Leo DiCaprio gets lost in a dream within a dream within a dream within a ...", | ||
| metadata: { year: 2010, director: "Christopher Nolan", rating: 8.2 }, | ||
| }), | ||
| new Document({ | ||
| pageContent: | ||
| "A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea", | ||
| metadata: { year: 2006, director: "Satoshi Kon", rating: 8.6 }, | ||
| }), | ||
| new Document({ | ||
| pageContent: | ||
| "A bunch of normal-sized women are supremely wholesome and some men pine after them", | ||
| metadata: { year: 2019, director: "Greta Gerwig", rating: 8.3 }, | ||
| }), | ||
| new Document({ | ||
| pageContent: "Toys come alive and have a blast doing so", | ||
| metadata: { year: 1995, genre: "animated" }, | ||
| }), | ||
| new Document({ | ||
| pageContent: "Three men walk into the Zone, three men walk out of the Zone", | ||
| metadata: { | ||
| year: 1979, | ||
| director: "Andrei Tarkovsky", | ||
| genre: "science fiction", | ||
| rating: 9.9, | ||
| }, | ||
| }), | ||
| ]; | ||
|
|
||
| /** | ||
| * Next, we define the attributes we want to be able to query on. | ||
| * in this case, we want to be able to query on the genre, year, director, rating, and length of the movie. | ||
| * We also provide a description of each attribute and the type of the attribute. | ||
| * This is used to generate the query prompts. | ||
| */ | ||
| const attributeInfo: AttributeInfo[] = [ | ||
| { | ||
| name: "genre", | ||
| description: "The genre of the movie", | ||
| type: "string or array of strings", | ||
| }, | ||
| { | ||
| name: "year", | ||
| description: "The year the movie was released", | ||
| type: "number", | ||
| }, | ||
| { | ||
| name: "director", | ||
| description: "The director of the movie", | ||
| type: "string", | ||
| }, | ||
| { | ||
| name: "rating", | ||
| description: "The rating of the movie (1-10)", | ||
| type: "number", | ||
| }, | ||
| { | ||
| name: "length", | ||
| description: "The length of the movie in minutes", | ||
| type: "number", | ||
| }, | ||
| ]; | ||
|
|
||
| /** | ||
| * Next, we instantiate a vector store. This is where we store the embeddings of the documents. | ||
| * We also need to provide an embeddings object. This is used to embed the documents. | ||
| */ | ||
|
|
||
| const QDRANT_URL = "http://127.0.0.1:6333"; | ||
| const QDRANT_COLLECTION_NAME = "some-collection-name"; | ||
|
|
||
| const client = new QdrantClient({ url: QDRANT_URL }); | ||
|
|
||
| const embeddings = new OpenAIEmbeddings(); | ||
| const llm = new OpenAI(); | ||
| const documentContents = "Brief summary of a movie"; | ||
| const vectorStore = await QdrantVectorStore.fromDocuments(docs, embeddings, { | ||
| client, | ||
| collectionName: QDRANT_COLLECTION_NAME, | ||
| }); | ||
| const selfQueryRetriever = SelfQueryRetriever.fromLLM({ | ||
| llm, | ||
| vectorStore, | ||
| documentContents, | ||
| attributeInfo, | ||
| /** | ||
| * We need to create a basic translator that translates the queries into a | ||
| * filter format that the vector store can understand. We provide a basic translator | ||
| * translator here, but you can create your own translator by extending BaseTranslator | ||
| * abstract class. Note that the vector store needs to support filtering on the metadata | ||
| * attributes you want to query on. | ||
| */ | ||
| structuredQueryTranslator: new QdrantTranslator(), | ||
| }); | ||
|
|
||
| /** | ||
| * Now we can query the vector store. | ||
| * We can ask questions like "Which movies are less than 90 minutes?" or "Which movies are rated higher than 8.5?". | ||
| * We can also ask questions like "Which movies are either comedy or drama and are less than 90 minutes?". | ||
| * The retriever will automatically convert these questions into queries that can be used to retrieve documents. | ||
| */ | ||
| const query1 = await selfQueryRetriever.getRelevantDocuments( | ||
| "Which movies are less than 90 minutes?" | ||
| ); | ||
| const query2 = await selfQueryRetriever.getRelevantDocuments( | ||
| "Which movies are rated higher than 8.5?" | ||
| ); | ||
| const query3 = await selfQueryRetriever.getRelevantDocuments( | ||
| "Which cool movies are directed by Greta Gerwig?" | ||
| ); | ||
| const query4 = await selfQueryRetriever.getRelevantDocuments( | ||
| "Which movies are either comedy or drama and are less than 90 minutes?" | ||
| ); | ||
| console.log(query1, query2, query3, query4); |
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
Oops, something went wrong.