feat: adding azion edgesql integration to langchain-community

docs/core_docs/docs/integrations/retrievers/azion-edgesql.mdx

@@ -0,0 +1,53 @@
+### Azion Edge SQL Retriever
+
+The `AzionRetriever` is used to perform advanced search operations, including hybrid and similarity searches directly on Azion's Edge Plataform using Edge SQL. Make sure to install the `@langchain/community` package to use this retriever. Besides that, you will need an Azion account and a Token to use the Azion API, configuring it as environment variable `AZION_TOKEN`.
+
+```typescript
+import { AzionRetriever } from "@langchain/community/retrievers/azion";
+import { OpenAIEmbeddings, ChatOpenAI } from "@langchain/openai";
+
+// Initialize the retriever
+const embeddingModel = new OpenAIEmbeddings({ model: "text-embedding-3-small" });
+// Initialize the entity extractor model to extract the entities to perform Full Text Search operations
+const entityExtractor = new ChatOpenAI({ model: "gpt-4o-mini" });
+
+// Initialize the retriever
+const retriever = new AzionRetriever(embeddingModel, entityExtractor, {
+  dbName: "mydb",
+  similarityK: 2,
+  ftsK: 2,
+  searchType: "hybrid",
+  // Filter documents by language = "en" AND topic IN ("nature", "biology")
+  filters: [
+    // Only return English language documents
+    { column: "language", operator: "=", value: "en" },
+    // Only return documents with topics of nature or biology
+    { column: "topic", operator: "IN", value: "'nature', 'biology'" }
+  ],
+  // Return only the topic and language metadata
+  metadataItems: ["topic", "language"]
+});
+
+// Perform a search
+const documents = await retriever._getRelevantDocuments("Australia");
+console.log(documents);
+```
+
+Using AzionRetriever as a tool in an agent requires the `createRetrieverTool` function to wrap the retriever:
+
+```typescript
+import {createRetrieverTool} from "@langchain/core/tools";
+import {AzionRetriever} from "./src/function/AzionRetriever";
+
+const retriever = new AzionRetriever(embeddingModel, entityExtractor, {
+  dbName: "mydb",
+  similarityK: 2,
+  ftsK: 2,
+});
+
+const retrieverTool = createRetrieverTool(retriever, {
+  name: "AzionRetriever",
+  description: "A tool that retrieves documents from a vector database"
+});
+
+```

docs/core_docs/docs/integrations/vectorstores/azion-edgesql.mdx

@@ -0,0 +1,39 @@
+### Azion Edge SQL Vector Store
+The `AzionVectorStore` is used to manage and search through a collection of documents using vector embeddings, directly on Azion's Edge Plataform using Edge SQL. Make sure to install the `@langchain/community` package to use this vector store. Besides that, you will need an Azion account and a Token to use the Azion API, configuring it as environment variable `AZION_TOKEN`.
+
+```typescript
+import { AzionVectorStore } from "@langchain/community/vectorstores/azionedgesql";
+import { OpenAIEmbeddings } from "@langchain/openai";
+import { Document } from "@langchain/core/documents";
+
+// Initialize the vector store
+const embeddingModel = new OpenAIEmbeddings({ model: "text-embedding-3-small" });
+const vectorStore = new AzionVectorStore(embeddingModel, { dbName: "mydb", tableName: "documents" });
+
+// Setup database with hybrid search and metadata columns
+await vectorStore.setupDatabase({
+  columns: ["topic", "language"],
+  mode: "hybrid"
+});
+
+//OR you can setup the database with the static method createDatabase
+//const vectorStore = await AzionVectorStore.createDatabase(embeddingModel,{dbName:"mydb", tableName:"documents"}, {columns: ["topic", "language"], mode: "hybrid"});
+
+// Add documents to the vector store
+await vectorStore.addDocuments([
+  new Document({ pageContent: "Australia is known for its unique wildlife", metadata: { topic: "nature", language: "en" } }),
+  // Add more documents as needed
+]);
+
+// Perform a similarity search
+const results = await vectorStore.AzionSimilaritySearch("Australia", { kvector: 1, metadataItems: ["topic"] });
+
+// OR
+// Perform a full text search
+const results = await vectorStore.AzionFullTextSearch("Australia", { kfts: 1, metadataItems: ["topic"] });
+
+// OR
+// Perform a hybrid search
+const results = await vectorStore.AzionHybridSearch("Australia", { kfts: 1, kvector: 1, metadataItems: ["topic"] });
+console.log(results);
+```

libs/langchain-community/langchain.config.js

@@ -117,6 +117,7 @@ export const config = {
     // vectorstores
     "vectorstores/analyticdb": "vectorstores/analyticdb",
     "vectorstores/astradb": "vectorstores/astradb",
+    "vectorstores/azion_edgesql": "vectorstores/azion_edgesql",
     "vectorstores/azure_aisearch": "vectorstores/azure_aisearch",
     "vectorstores/azure_cosmosdb": "vectorstores/azure_cosmosdb",
     "vectorstores/cassandra": "vectorstores/cassandra",
@@ -196,6 +197,7 @@ export const config = {
     // retrievers
     "retrievers/amazon_kendra": "retrievers/amazon_kendra",
     "retrievers/amazon_knowledge_base": "retrievers/amazon_knowledge_base",
+    "retrievers/azion_edgesql": "retrievers/azion_edgesql",
     "retrievers/bm25": "retrievers/bm25",
     "retrievers/chaindesk": "retrievers/chaindesk",
     "retrievers/databerry": "retrievers/databerry",
@@ -377,6 +379,7 @@ export const config = {
     "llms/layerup_security",
     "vectorstores/analyticdb",
     "vectorstores/astradb",
+    "vectorstores/azion_edgesql",
     "vectorstores/azure_aisearch",
     "vectorstores/azure_cosmosdb",
     "vectorstores/cassandra",
@@ -434,6 +437,7 @@ export const config = {
     "chat_models/zhipuai",
     "retrievers/amazon_kendra",
     "retrievers/amazon_knowledge_base",
+    "retrievers/azion_edgesql",
     "retrievers/dria",
     "retrievers/metal",
     "retrievers/supabase",