@langchain/pinecone - npm Package Compare versions

Comparing version 0.0.8 to 0.0.9

dist/vectorstores.d.ts

@@ -45,4 +45,133 @@ import { RecordMetadata, Index as PineconeIndex } from "@pinecone-database/pinecone";
 /**
- * Class for managing and operating vector search applications with
- * Pinecone, the cloud-native high-scale vector database
+ * Pinecone vector store integration.
+ *
+ * Setup:
+ * Install `@langchain/pinecone` and `@pinecone-database/pinecone` to pass a client in.
+ *
+ * ```bash
+ * npm install @langchain/pinecone @pinecone-database/pinecone
+ * ```
+ *
+ * ## [Constructor args](https://api.js.langchain.com/classes/_langchain_pinecone.PineconeStore.html#constructor)
+ *
+ * <details open>
+ * <summary><strong>Instantiate</strong></summary>
+ *
+ * ```typescript
+ * import { PineconeStore } from '@langchain/pinecone';
+ * // Or other embeddings
+ * import { OpenAIEmbeddings } from '@langchain/openai';
+ *
+ * import { Pinecone as PineconeClient } from "@pinecone-database/pinecone";
+ *
+ * const pinecone = new PineconeClient();
+ *
+ * // Will automatically read the PINECONE_API_KEY and PINECONE_ENVIRONMENT env vars
+ * const pineconeIndex = pinecone.Index(process.env.PINECONE_INDEX!);
+ *
+ * const embeddings = new OpenAIEmbeddings({
+ *   model: "text-embedding-3-small",
+ * });
+ *
+ * const vectorStore = await PineconeStore.fromExistingIndex(embeddings, {
+ *   pineconeIndex,
+ *   // Maximum number of batch requests to allow at once. Each batch is 1000 vectors.
+ *   maxConcurrency: 5,
+ *   // You can pass a namespace here too
+ *   // namespace: "foo",
+ * });
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Add documents</strong></summary>
+ *
+ * ```typescript
+ * import type { Document } from '@langchain/core/documents';
+ *
+ * const document1 = { pageContent: "foo", metadata: { baz: "bar" } };
+ * const document2 = { pageContent: "thud", metadata: { bar: "baz" } };
+ * const document3 = { pageContent: "i will be deleted :(", metadata: {} };
+ *
+ * const documents: Document[] = [document1, document2, document3];
+ * const ids = ["1", "2", "3"];
+ * await vectorStore.addDocuments(documents, { ids });
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Delete documents</strong></summary>
+ *
+ * ```typescript
+ * await vectorStore.delete({ ids: ["3"] });
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Similarity search</strong></summary>
+ *
+ * ```typescript
+ * const results = await vectorStore.similaritySearch("thud", 1);
+ * for (const doc of results) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * thud [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with filter</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithFilter = await vectorStore.similaritySearch("thud", 1, { baz: "bar" });
+ *
+ * for (const doc of resultsWithFilter) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * foo [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with score</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithScore = await vectorStore.similaritySearchWithScore("qux", 1);
+ * for (const [doc, score] of resultsWithScore) {
+ *   console.log(`* [SIM=${score.toFixed(6)}] ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * [SIM=0.000000] qux [{"bar":"baz","baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>As a retriever</strong></summary>
+ *
+ * ```typescript
+ * const retriever = vectorStore.asRetriever({
+ *   searchType: "mmr", // Leave blank for standard similarity search
+ *   k: 1,
+ * });
+ * const resultAsRetriever = await retriever.invoke("thud");
+ * console.log(resultAsRetriever);
+ *
+ * // Output: [Document({ metadata: { "baz":"bar" }, pageContent: "thud" })]
+ * ```
+ * </details>
+ *
+ * <br />
  */
@@ -91,2 +220,8 @@ export declare class PineconeStore extends VectorStore {
     /**
+     * Format the matching results from the Pinecone query.
+     * @param matches Matching results from the Pinecone query.
+     * @returns An array of arrays, where each inner array contains a document and its score.
+     */
+    private _formatMatches;
+    /**
      * Method that performs a similarity search in the Pinecone database and
@@ -93,0 +228,0 @@ * returns the results along with their scores.

dist/vectorstores.js

@@ -10,4 +10,133 @@ import * as uuid from "uuid";
 /**
- * Class for managing and operating vector search applications with
- * Pinecone, the cloud-native high-scale vector database
+ * Pinecone vector store integration.
+ *
+ * Setup:
+ * Install `@langchain/pinecone` and `@pinecone-database/pinecone` to pass a client in.
+ *
+ * ```bash
+ * npm install @langchain/pinecone @pinecone-database/pinecone
+ * ```
+ *
+ * ## [Constructor args](https://api.js.langchain.com/classes/_langchain_pinecone.PineconeStore.html#constructor)
+ *
+ * <details open>
+ * <summary><strong>Instantiate</strong></summary>
+ *
+ * ```typescript
+ * import { PineconeStore } from '@langchain/pinecone';
+ * // Or other embeddings
+ * import { OpenAIEmbeddings } from '@langchain/openai';
+ *
+ * import { Pinecone as PineconeClient } from "@pinecone-database/pinecone";
+ *
+ * const pinecone = new PineconeClient();
+ *
+ * // Will automatically read the PINECONE_API_KEY and PINECONE_ENVIRONMENT env vars
+ * const pineconeIndex = pinecone.Index(process.env.PINECONE_INDEX!);
+ *
+ * const embeddings = new OpenAIEmbeddings({
+ *   model: "text-embedding-3-small",
+ * });
+ *
+ * const vectorStore = await PineconeStore.fromExistingIndex(embeddings, {
+ *   pineconeIndex,
+ *   // Maximum number of batch requests to allow at once. Each batch is 1000 vectors.
+ *   maxConcurrency: 5,
+ *   // You can pass a namespace here too
+ *   // namespace: "foo",
+ * });
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Add documents</strong></summary>
+ *
+ * ```typescript
+ * import type { Document } from '@langchain/core/documents';
+ *
+ * const document1 = { pageContent: "foo", metadata: { baz: "bar" } };
+ * const document2 = { pageContent: "thud", metadata: { bar: "baz" } };
+ * const document3 = { pageContent: "i will be deleted :(", metadata: {} };
+ *
+ * const documents: Document[] = [document1, document2, document3];
+ * const ids = ["1", "2", "3"];
+ * await vectorStore.addDocuments(documents, { ids });
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Delete documents</strong></summary>
+ *
+ * ```typescript
+ * await vectorStore.delete({ ids: ["3"] });
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Similarity search</strong></summary>
+ *
+ * ```typescript
+ * const results = await vectorStore.similaritySearch("thud", 1);
+ * for (const doc of results) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * thud [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with filter</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithFilter = await vectorStore.similaritySearch("thud", 1, { baz: "bar" });
+ *
+ * for (const doc of resultsWithFilter) {
+ *   console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * foo [{"baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ *
+ * <details>
+ * <summary><strong>Similarity search with score</strong></summary>
+ *
+ * ```typescript
+ * const resultsWithScore = await vectorStore.similaritySearchWithScore("qux", 1);
+ * for (const [doc, score] of resultsWithScore) {
+ *   console.log(`* [SIM=${score.toFixed(6)}] ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
+ * }
+ * // Output: * [SIM=0.000000] qux [{"bar":"baz","baz":"bar"}]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>As a retriever</strong></summary>
+ *
+ * ```typescript
+ * const retriever = vectorStore.asRetriever({
+ *   searchType: "mmr", // Leave blank for standard similarity search
+ *   k: 1,
+ * });
+ * const resultAsRetriever = await retriever.invoke("thud");
+ * console.log(resultAsRetriever);
+ *
+ * // Output: [Document({ metadata: { "baz":"bar" }, pageContent: "thud" })]
+ * ```
+ * </details>
+ *
+ * <br />
  */
@@ -186,2 +315,26 @@ export class PineconeStore extends VectorStore {
     /**
+     * Format the matching results from the Pinecone query.
+     * @param matches Matching results from the Pinecone query.
+     * @returns An array of arrays, where each inner array contains a document and its score.
+     */
+    _formatMatches(matches = []) {
+        const documentsWithScores = [];
+        for (const record of matches) {
+            const { id, score, metadata: { [this.textKey]: pageContent, ...metadata } = {
+                [this.textKey]: "",
+            }, } = record;
+            if (score) {
+                documentsWithScores.push([
+                    new Document({
+                        id,
+                        pageContent: pageContent.toString(),
+                        metadata,
+                    }),
+                    score,
+                ]);
+            }
+        }
+        return documentsWithScores;
+    }
+    /**
      * Method that performs a similarity search in the Pinecone database and
@@ -195,14 +348,5 @@ * returns the results along with their scores.
     async similaritySearchVectorWithScore(query, k, filter) {
-        const results = await this._runPineconeQuery(query, k, filter);
-        const result = [];
-        if (results.matches) {
-            for (const res of results.matches) {
-                const { [this.textKey]: pageContent, ...metadata } = (res.metadata ??
-                    {});
-                if (res.score) {
-                    result.push([new Document({ metadata, pageContent }), res.score]);
-                }
-            }
-        }
-        return result;
+        const { matches = [] } = await this._runPineconeQuery(query, k, filter);
+        const records = this._formatMatches(matches);
+        return records;
     }
@@ -226,15 +370,8 @@ /**
         const results = await this._runPineconeQuery(queryEmbedding, options.fetchK ?? 20, options.filter, { includeValues: true });
-        const matches = results?.matches ?? [];
+        const { matches = [] } = results;
         const embeddingList = matches.map((match) => match.values);
         const mmrIndexes = maximalMarginalRelevance(queryEmbedding, embeddingList, options.lambda, options.k);
         const topMmrMatches = mmrIndexes.map((idx) => matches[idx]);
-        const finalResult = [];
-        for (const res of topMmrMatches) {
-            const { [this.textKey]: pageContent, ...metadata } = (res.metadata ??
-                {});
-            if (res.score) {
-                finalResult.push(new Document({ metadata, pageContent }));
-            }
-        }
-        return finalResult;
+        const records = this._formatMatches(topMmrMatches);
+        return records.map(([doc, _score]) => doc);
     }
@@ -241,0 +378,0 @@ /**

package.json

 {
   "name": "@langchain/pinecone",
-  "version": "0.0.8",
+  "version": "0.0.9",
   "description": "LangChain integration for Pinecone's vector database",
@@ -18,3 +18,3 @@ "type": "module",
     "build": "yarn turbo:command build:internal --filter=@langchain/pinecone",
-    "build:internal": "yarn lc-build:v2 --create-entrypoints --pre --tree-shaking",
+    "build:internal": "yarn lc_build_v2 --create-entrypoints --pre --tree-shaking",
     "build:esm": "NODE_OPTIONS=--max-old-space-size=4096 tsc --outDir dist/ && rm -rf dist/tests dist/**/tests",
@@ -52,3 +52,3 @@ "build:cjs": "NODE_OPTIONS=--max-old-space-size=4096 tsc --outDir dist-cjs/ -p tsconfig.cjs.json && yarn move-cjs-to-dist && rm -rf dist-cjs",
     "@langchain/openai": "workspace:*",
-    "@langchain/scripts": "~0.0.14",
+    "@langchain/scripts": "~0.0.20",
     "@swc/core": "^1.3.90",
@@ -71,3 +71,3 @@ "@swc/jest": "^0.2.29",
     "prettier": "^2.8.3",
-    "release-it": "^15.10.1",
+    "release-it": "^17.6.0",
     "rollup": "^4.5.2",
@@ -74,0 +74,0 @@ "ts-jest": "^29.1.0",

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

55372

increased by26%

Lines of code

1288

increased by46.53%

No dependency changes