feat(cosmosdbnosql): Add Semantic Cache Integration

docs/core_docs/.gitignore

@@ -224,6 +224,18 @@ docs/versions/migrating_memory/chat_history.md
 docs/versions/migrating_memory/chat_history.mdx
 docs/troubleshooting/errors/INVALID_TOOL_RESULTS.md
 docs/troubleshooting/errors/INVALID_TOOL_RESULTS.mdx
+docs/integrations/toolkits/vectorstore.md
+docs/integrations/toolkits/vectorstore.mdx
+docs/integrations/toolkits/sql.md
+docs/integrations/toolkits/sql.mdx
+docs/integrations/toolkits/openapi.md
+docs/integrations/toolkits/openapi.mdx
+docs/integrations/tools/tavily_search.md
+docs/integrations/tools/tavily_search.mdx
+docs/integrations/tools/exa_search.md
+docs/integrations/tools/exa_search.mdx
+docs/integrations/tools/duckduckgo_search.md
+docs/integrations/tools/duckduckgo_search.mdx
 docs/integrations/vectorstores/weaviate.md
 docs/integrations/vectorstores/weaviate.mdx
 docs/integrations/vectorstores/upstash.md
@@ -250,22 +262,20 @@ docs/integrations/vectorstores/elasticsearch.md
 docs/integrations/vectorstores/elasticsearch.mdx
 docs/integrations/vectorstores/chroma.md
 docs/integrations/vectorstores/chroma.mdx
-docs/integrations/tools/tavily_search.md
-docs/integrations/tools/tavily_search.mdx
-docs/integrations/tools/exa_search.md
-docs/integrations/tools/exa_search.mdx
-docs/integrations/tools/duckduckgo_search.md
-docs/integrations/tools/duckduckgo_search.mdx
-docs/integrations/toolkits/vectorstore.md
-docs/integrations/toolkits/vectorstore.mdx
-docs/integrations/toolkits/sql.md
-docs/integrations/toolkits/sql.mdx
-docs/integrations/toolkits/openapi.md
-docs/integrations/toolkits/openapi.mdx
 docs/integrations/stores/in_memory.md
 docs/integrations/stores/in_memory.mdx
 docs/integrations/stores/file_system.md
 docs/integrations/stores/file_system.mdx
+docs/integrations/retrievers/tavily.md
+docs/integrations/retrievers/tavily.mdx
+docs/integrations/retrievers/kendra-retriever.md
+docs/integrations/retrievers/kendra-retriever.mdx
+docs/integrations/retrievers/exa.md
+docs/integrations/retrievers/exa.mdx
+docs/integrations/retrievers/bm25.md
+docs/integrations/retrievers/bm25.mdx
+docs/integrations/retrievers/bedrock-knowledge-bases.md
+docs/integrations/retrievers/bedrock-knowledge-bases.mdx
 docs/integrations/text_embedding/togetherai.md
 docs/integrations/text_embedding/togetherai.mdx
 docs/integrations/text_embedding/openai.md
@@ -274,6 +284,8 @@ docs/integrations/text_embedding/ollama.md
 docs/integrations/text_embedding/ollama.mdx
 docs/integrations/text_embedding/mistralai.md
 docs/integrations/text_embedding/mistralai.mdx
+docs/integrations/text_embedding/ibm.md
+docs/integrations/text_embedding/ibm.mdx
 docs/integrations/text_embedding/google_vertex_ai.md
 docs/integrations/text_embedding/google_vertex_ai.mdx
 docs/integrations/text_embedding/google_generativeai.md
@@ -296,6 +308,8 @@ docs/integrations/llms/ollama.md
 docs/integrations/llms/ollama.mdx
 docs/integrations/llms/mistral.md
 docs/integrations/llms/mistral.mdx
+docs/integrations/llms/ibm.md
+docs/integrations/llms/ibm.mdx
 docs/integrations/llms/google_vertex_ai.md
 docs/integrations/llms/google_vertex_ai.mdx
 docs/integrations/llms/fireworks.md
@@ -310,32 +324,6 @@ docs/integrations/llms/azure.md
 docs/integrations/llms/azure.mdx
 docs/integrations/llms/arcjet.md
 docs/integrations/llms/arcjet.mdx
-docs/integrations/retrievers/tavily.md
-docs/integrations/retrievers/tavily.mdx
-docs/integrations/retrievers/kendra-retriever.md
-docs/integrations/retrievers/kendra-retriever.mdx
-docs/integrations/retrievers/exa.md
-docs/integrations/retrievers/exa.mdx
-docs/integrations/retrievers/bm25.md
-docs/integrations/retrievers/bm25.mdx
-docs/integrations/retrievers/bedrock-knowledge-bases.md
-docs/integrations/retrievers/bedrock-knowledge-bases.mdx
-docs/integrations/retrievers/self_query/weaviate.md
-docs/integrations/retrievers/self_query/weaviate.mdx
-docs/integrations/retrievers/self_query/vectara.md
-docs/integrations/retrievers/self_query/vectara.mdx
-docs/integrations/retrievers/self_query/supabase.md
-docs/integrations/retrievers/self_query/supabase.mdx
-docs/integrations/retrievers/self_query/qdrant.md
-docs/integrations/retrievers/self_query/qdrant.mdx
-docs/integrations/retrievers/self_query/pinecone.md
-docs/integrations/retrievers/self_query/pinecone.mdx
-docs/integrations/retrievers/self_query/memory.md
-docs/integrations/retrievers/self_query/memory.mdx
-docs/integrations/retrievers/self_query/hnswlib.md
-docs/integrations/retrievers/self_query/hnswlib.mdx
-docs/integrations/retrievers/self_query/chroma.md
-docs/integrations/retrievers/self_query/chroma.mdx
 docs/integrations/chat/togetherai.md
 docs/integrations/chat/togetherai.mdx
 docs/integrations/chat/openai.md
@@ -344,6 +332,8 @@ docs/integrations/chat/ollama.md
 docs/integrations/chat/ollama.mdx
 docs/integrations/chat/mistral.md
 docs/integrations/chat/mistral.mdx
+docs/integrations/chat/ibm.md
+docs/integrations/chat/ibm.mdx
 docs/integrations/chat/groq.md
 docs/integrations/chat/groq.mdx
 docs/integrations/chat/google_vertex_ai.md
@@ -366,6 +356,22 @@ docs/integrations/chat/arcjet.md
 docs/integrations/chat/arcjet.mdx
 docs/integrations/chat/anthropic.md
 docs/integrations/chat/anthropic.mdx
+docs/integrations/retrievers/self_query/weaviate.md
+docs/integrations/retrievers/self_query/weaviate.mdx
+docs/integrations/retrievers/self_query/vectara.md
+docs/integrations/retrievers/self_query/vectara.mdx
+docs/integrations/retrievers/self_query/supabase.md
+docs/integrations/retrievers/self_query/supabase.mdx
+docs/integrations/retrievers/self_query/qdrant.md
+docs/integrations/retrievers/self_query/qdrant.mdx
+docs/integrations/retrievers/self_query/pinecone.md
+docs/integrations/retrievers/self_query/pinecone.mdx
+docs/integrations/retrievers/self_query/memory.md
+docs/integrations/retrievers/self_query/memory.mdx
+docs/integrations/retrievers/self_query/hnswlib.md
+docs/integrations/retrievers/self_query/hnswlib.mdx
+docs/integrations/retrievers/self_query/chroma.md
+docs/integrations/retrievers/self_query/chroma.mdx
 docs/integrations/document_loaders/web_loaders/web_puppeteer.md
 docs/integrations/document_loaders/web_loaders/web_puppeteer.mdx
 docs/integrations/document_loaders/web_loaders/web_cheerio.md

docs/core_docs/docs/integrations/llm_caching/azure_cosmosdb_nosql.mdx

@@ -0,0 +1,40 @@
+# Azure Cosmos DB NoSQL Semantic Cache
+
+> The Semantic Cache feature is supported with Azure Cosmos DB for NoSQL integration, enabling users to retrieve cached responses based on semantic similarity between the user input and previously cached results. It leverages [AzureCosmosDBNoSQLVectorStore](/docs/integrations/vectorstores/azure_cosmosdb_nosql), which stores vector embeddings of cached prompts. These embeddings enable similarity-based searches, allowing the system to retrieve relevant cached results.
+
+If you don't have an Azure account, you can [create a free account](https://azure.microsoft.com/free/) to get started.
+
+## Setup
+
+You'll first need to install the [`@langchain/azure-cosmosdb`](https://www.npmjs.com/package/@langchain/azure-cosmosdb) package:
+
+import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
+
+<IntegrationInstallTooltip></IntegrationInstallTooltip>
+
+```bash npm2yarn
+npm install @langchain/azure-cosmosdb @langchain/core
+```
+
+You'll also need to have an Azure Cosmos DB for NoSQL instance running. You can deploy a free version on Azure Portal without any cost, following [this guide](https://learn.microsoft.com/azure/cosmos-db/nosql/quickstart-portal).
+
+Once you have your instance running, make sure you have the connection string. If you are using Managed Identity, you need to have the endpoint. You can find them in the Azure Portal, under the "Settings / Keys" section of your instance.
+
+import CodeBlock from "@theme/CodeBlock";
+
+:::info
+
+When using Azure Managed Identity and role-based access control, you must ensure that the database and container have been created beforehand. RBAC does not provide permissions to create databases and containers. You can get more information about the permission model in the [Azure Cosmos DB documentation](https://learn.microsoft.com/azure/cosmos-db/how-to-setup-rbac#permission-model).
+
+:::
+
+## Usage example
+
+import Example from "@examples/caches/azure_cosmosdb_nosql/azure_cosmosdb_nosql.ts";
+
+<CodeBlock language="typescript">{Example}</CodeBlock>
+
+## Related
+
+- Vector store [conceptual guide](/docs/concepts/#vectorstores)
+- Vector store [how-to guides](/docs/how_to/#vectorstores)

docs/core_docs/docs/integrations/llm_caching/index.mdx

@@ -0,0 +1,14 @@
+---
+sidebar_class_name: hidden
+hide_table_of_contents: true
+---
+
+# Model caches
+
+[Caching LLM calls](/docs/how_to/chat_model_caching) can be useful for testing, cost savings, and speed.
+
+Below are some integrations that allow you to cache results of individual LLM calls using different caches with different strategies.
+
+import { IndexTable } from "@theme/FeatureTables";
+
+<IndexTable />

docs/core_docs/docs/integrations/platforms/microsoft.mdx

@@ -132,6 +132,24 @@ See a [usage example](/docs/integrations/vectorstores/azure_cosmosdb_mongodb).
 import { AzureCosmosDBMongoDBVectorStore } from "@langchain/azure-cosmosdb";
 ```
 
+## Semantic Cache
+
+### Azure Cosmos DB NoSQL Semantic Cache
+
+> The Semantic Cache feature is supported with Azure Cosmos DB for NoSQL integration, enabling users to retrieve cached responses based on semantic similarity between the user input and previously cached results. It leverages [AzureCosmosDBNoSQLVectorStore](/docs/integrations/vectorstores/azure_cosmosdb_nosql), which stores vector embeddings of cached prompts. These embeddings enable similarity-based searches, allowing the system to retrieve relevant cached results.
+
+<IntegrationInstallTooltip></IntegrationInstallTooltip>
+
+```bash npm2yarn
+npm install @langchain/azure-cosmosdb @langchain/core
+```
+
+See a [usage example](/docs/integrations/llm_caching/azure_cosmosdb_nosql).
+
+```typescript
+import { AzureCosmosDBNoSQLSemanticCache } from "@langchain/azure-cosmosdb";
+```
+
 ## Document loaders
 
 ### Azure Blob Storage

docs/core_docs/sidebars.js

@@ -335,6 +335,22 @@ module.exports = {
                 slug: "integrations/document_transformers",
               },
             },
+            {
+              type: "category",
+              label: "Model caches",
+              collapsible: false,
+              items: [
+                {
+                  type: "autogenerated",
+                  dirName: "integrations/llm_caching",
+                  className: "hidden",
+                },
+              ],
+              link: {
+                type: "doc",
+                id: "integrations/llm_caching/index",
+              },
+            },
             {
               type: "category",
               label: "Graphs",

examples/src/caches/azure_cosmosdb_nosql/azure_cosmosdb_nosql.ts

@@ -0,0 +1,49 @@
+import {
+  AzureCosmosDBNoSQLConfig,
+  AzureCosmosDBNoSQLSemanticCache,
+} from "@langchain/azure-cosmosdb";
+import { ChatOpenAI, OpenAIEmbeddings } from "@langchain/openai";
+
+const embeddings = new OpenAIEmbeddings();
+const config: AzureCosmosDBNoSQLConfig = {
+  databaseName: "<DATABASE_NAME>",
+  containerName: "<CONTAINER_NAME>",
+  // use endpoint to initiate client with managed identity
+  connectionString: "<CONNECTION_STRING>",
+};
+
+/**
+ * Sets the threshold similarity score for returning cached results based on vector distance.
+ * Cached output is returned only if the similarity score meets or exceeds this threshold;
+ * otherwise, a new result is generated. Default is 0.6, adjustable via the constructor
+ * to suit various distance functions and use cases.
+ * (see: https://learn.microsoft.com/en-us/azure/cosmos-db/nosql/query/vectordistance).
+ */
+
+const similarityScoreThreshold = 0.5;
+const cache = new AzureCosmosDBNoSQLSemanticCache(
+  embeddings,
+  config,
+  similarityScoreThreshold
+);
+
+const model = new ChatOpenAI({ cache });
+
+// Invoke the model to perform an action
+const response1 = await model.invoke("Do something random!");
+console.log(response1);
+/*
+  AIMessage {
+    content: "Sure! I'll generate a random number for you: 37",
+    additional_kwargs: {}
+  }
+*/
+
+const response2 = await model.invoke("Do something random!");
+console.log(response2);
+/*
+  AIMessage {
+    content: "Sure! I'll generate a random number for you: 37",
+    additional_kwargs: {}
+  }
+*/

libs/langchain-azure-cosmosdb/src/azure_cosmosdb_nosql.ts

@@ -78,7 +78,7 @@ export interface AzureCosmosDBNoSQLConfig
   readonly metadataKey?: string;
 }
 
-const USER_AGENT_PREFIX = "langchainjs-azure-cosmosdb-nosql";
+const USER_AGENT_SUFFIX = "langchainjs-cdbnosql-vectorstore-javascript";
 
 /**
  * Azure Cosmos DB for NoSQL vCore vector store.
@@ -151,14 +151,14 @@ export class AzureCosmosDBNoSQLVectorStore extends VectorStore {
         this.client = new CosmosClient({
           endpoint,
           key,
-          userAgentSuffix: USER_AGENT_PREFIX,
+          userAgentSuffix: USER_AGENT_SUFFIX,
         });
       } else {
         // Use managed identity
         this.client = new CosmosClient({
           endpoint,
           aadCredentials: dbConfig.credentials ?? new DefaultAzureCredential(),
-          userAgentSuffix: USER_AGENT_PREFIX,
+          userAgentSuffix: USER_AGENT_SUFFIX,
         } as CosmosClientOptions);
       }
     }