chore: lint files

examples/src/agents/quickstart.ts

@@ -37,9 +37,7 @@ const vectorstore = await MemoryVectorStore.fromDocuments(
 );
 const retriever = vectorstore.asRetriever();
 
-const retrieverResult = await retriever.invoke(
-  "how to upload a dataset"
-);
+const retrieverResult = await retriever.invoke("how to upload a dataset");
 console.log(retrieverResult[0]);
 
 /*

examples/src/callbacks/trace_groups.ts

@@ -22,7 +22,10 @@ export const run = async () => {
     async (manager: CallbackManager, questions: string[]) => {
       await chain.invoke({ question: questions[0] }, manager);
       await chain.invoke({ question: questions[1] }, manager);
-      const finalResult = await chain.invoke({ question: questions[2] }, manager);
+      const finalResult = await chain.invoke(
+        { question: questions[2] },
+        manager
+      );
       return finalResult;
     },
     [

examples/src/chains/llm_chain_cancellation.ts

@@ -20,11 +20,13 @@ try {
   const res = await chain.invoke(
     { product: "colorful socks", signal: controller.signal },
     {
-      callbacks: [{
-        handleLLMNewToken(token: string) {
-          process.stdout.write(token);
-        }
-      }],
+      callbacks: [
+        {
+          handleLLMNewToken(token: string) {
+            process.stdout.write(token);
+          },
+        },
+      ],
     }
   );
 } catch (e) {

examples/src/chains/llm_chain_stream.ts

@@ -10,14 +10,17 @@ const prompt = PromptTemplate.fromTemplate(
 const chain = new LLMChain({ llm: model, prompt });
 
 // Call the chain with the inputs and a callback for the streamed tokens
-const res = await chain.invoke({ product: "colorful socks" }, {
-  callbacks: [
-    {
-      handleLLMNewToken(token: string) {
-        process.stdout.write(token);
+const res = await chain.invoke(
+  { product: "colorful socks" },
+  {
+    callbacks: [
+      {
+        handleLLMNewToken(token: string) {
+          process.stdout.write(token);
+        },
       },
-    },
-  ]
-});
+    ],
+  }
+);
 console.log({ res });
 // { res: { text: '\n\nKaleidoscope Socks' } }

examples/src/chat/overview.ts

@@ -38,19 +38,18 @@ export const run = async () => {
   // Sending two separate prompts in parallel, receiving two responses back
 
   const responseA = await chat.invoke([
-
-      new SystemMessage(
-        "You are a helpful assistant that translates English to French."
-      ),
-      new HumanMessage(
-        "Translate this sentence from English to French. I love programming."
-      ),
-      new SystemMessage(
-        "You are a helpful assistant that translates English to French."
-      ),
-      new HumanMessage(
-        "Translate this sentence from English to French. I love artificial intelligence."
-      ),
+    new SystemMessage(
+      "You are a helpful assistant that translates English to French."
+    ),
+    new HumanMessage(
+      "Translate this sentence from English to French. I love programming."
+    ),
+    new SystemMessage(
+      "You are a helpful assistant that translates English to French."
+    ),
+    new HumanMessage(
+      "Translate this sentence from English to French. I love artificial intelligence."
+    ),
   ]);
 
   console.log(responseA);

examples/src/experimental/babyagi/weather_with_tools.ts

@@ -52,7 +52,9 @@ const babyAGI = BabyAGI.fromLLM({
   maxIterations: 10,
 });
 
-await babyAGI.invoke({ objective: "Write a short weather report for SF today" });
+await babyAGI.invoke({
+  objective: "Write a short weather report for SF today",
+});
 /*
 
 *****TASK LIST*****

examples/src/indexes/vector_stores/vectara.ts

@@ -55,9 +55,7 @@ console.log(JSON.stringify(resultsWithScore, null, 2));
 */
 
 const retriever = new VectaraSummaryRetriever({ vectara: store, topK: 3 });
-const documents = await retriever.invoke(
-  "What were the women talking about?"
-);
+const documents = await retriever.invoke("What were the women talking about?");
 
 console.log(JSON.stringify(documents, null, 2));
 /*

examples/src/models/chat/chat.ts

@@ -26,18 +26,18 @@ export const run = async () => {
 
   // Similar to LLMs, you can also use `generate` to generate chat completions for multiple sets of messages.
   const responseC = await chat.invoke([
-      new SystemMessage(
-        "You are a helpful assistant that translates English to French."
-      ),
-      new HumanMessage(
-        "Translate this sentence from English to French. I love programming."
-      ),
-      new SystemMessage(
-        "You are a helpful assistant that translates English to French."
-      ),
-      new HumanMessage(
-        "Translate this sentence from English to French. I love artificial intelligence."
-      ),
+    new SystemMessage(
+      "You are a helpful assistant that translates English to French."
+    ),
+    new HumanMessage(
+      "Translate this sentence from English to French. I love programming."
+    ),
+    new SystemMessage(
+      "You are a helpful assistant that translates English to French."
+    ),
+    new HumanMessage(
+      "Translate this sentence from English to French. I love artificial intelligence."
+    ),
   ]);
   console.log(responseC);
   /*

examples/src/retrievers/hyde.ts

@@ -21,9 +21,7 @@ await vectorStore.addDocuments(
   ].map((pageContent) => new Document({ pageContent }))
 );
 
-const results = await retriever.invoke(
-  "What is my favourite food?"
-);
+const results = await retriever.invoke("What is my favourite food?");
 
 console.log(results);
 /*

examples/src/retrievers/parent_document_retriever_chunk_header.ts

@@ -48,9 +48,7 @@ await retriever.addDocuments(pamDocs, {
 
 // This will search child documents in vector store with the help of chunk header,
 // returning the unmodified parent documents
-const retrievedDocs = await retriever.invoke(
-  "What is Pam's favorite color?"
-);
+const retrievedDocs = await retriever.invoke("What is Pam's favorite color?");
 
 // Pam's favorite color is returned first!
 console.log(JSON.stringify(retrievedDocs, null, 2));

examples/src/retrievers/similarity_score_threshold.ts

@@ -22,9 +22,7 @@ const retriever = ScoreThresholdRetriever.fromVectorStore(vectorStore, {
   kIncrement: 2, // How much to increase K by each time. It'll fetch N results, then N + kIncrement, then N + kIncrement * 2, etc.
 });
 
-const result = await retriever.invoke(
-  "What are buildings made out of?"
-);
+const result = await retriever.invoke("What are buildings made out of?");
 
 console.log(result);
 

examples/src/retrievers/time-weighted-retriever.ts

@@ -22,9 +22,7 @@ const documents = [
 // so that the correct access history metadata is populated
 await retriever.addDocuments(documents);
 
-const results1 = await retriever.invoke(
-  "What is my favourite food?"
-);
+const results1 = await retriever.invoke("What is my favourite food?");
 
 console.log(results1);
 
@@ -34,9 +32,7 @@ console.log(results1);
 ]
  */
 
-const results2 = await retriever.invoke(
-  "What is my favourite food?"
-);
+const results2 = await retriever.invoke("What is my favourite food?");
 
 console.log(results2);