@promptbook/anthropic-claude - npm Package Compare versions

Comparing version 0.52.0-30 to 0.52.0-31

esm/typings/execution/plugins/llm-execution-tools/remote/startRemoteServer.d.ts

@@ -13,2 +13,3 @@ import type { IDestroyable } from 'destroyable';
 /**
+ * TODO: [⚖] Expose the library to be able to connect to same library via createPromptbookLibraryFromUrl
  * TODO: Handle progress - support streaming
@@ -15,0 +16,0 @@ * TODO: [🤹‍♂️] Do not hang up immediately but wait until client closes OR timeout

esm/typings/library/constructors/createPromptbookLibraryFromUrl.d.ts

@@ -28,3 +28,4 @@ import { string_url } from '../../types/typeAliases';
 /***
+ * TODO: [⚖] Compatible with remote server
  * TODO: [🍓][🚯] !!! Add to README and samples + maybe make `@promptbook/library` package
  */

package.json

 {
     "name": "@promptbook/anthropic-claude",
-    "version": "0.52.0-30",
+    "version": "0.52.0-31",
     "description": "Library to supercharge your use of large language models",
@@ -51,3 +51,3 @@ "private": false,
     "peerDependencies": {
-        "@promptbook/core": "0.52.0-30"
+        "@promptbook/core": "0.52.0-31"
     },
@@ -54,0 +54,0 @@ "main": "./umd/index.umd.js",

README.md

@@ -33,8 +33,99 @@ # ![Promptbook logo - cube with letters P and B](./other/design/logo-h1.png) Promptbook
 
+`@promptbook/anthropic-claude` integrates [Anthropic's Claude API](https://console.anthropic.com/) with [Promptbook](https://github.com/webgptorg/promptbook). It allows to execute Promptbooks with OpenAI Claude 2 and 3 models.
 
+## 🧡 Usage
 
+```typescript
+import {
+    createPromptbookExecutor,
+    createPromptbookLibraryFromDirectory,
+    assertsExecutionSuccessful,
+} from '@promptbook/core';
+import { JavascriptExecutionTools } from '@promptbook/execute-javascript';
+import { OpenAiExecutionTools } from '@promptbook/openai';
 
+// ▶ Create whole Promptbook library
+const library = await createPromptbookLibraryFromDirectory('./promptbook-library');
 
+// ▶ Get one Promptbook
+const promptbook = await library.getPromptbookByUrl(`https://promptbook.studio/my-library/write-article.ptbk.md`);
 
+// ▶ Prepare tools
+const tools = {
+    llm: new AnthropicClaudeExecutionTools({
+        isVerbose: true,
+        apiKey: process.env.ANTHROPIC_CLAUDE_API_KEY,
+    }),
+    script: [new JavascriptExecutionTools()],
+};
 
+// ▶ Create executor - the function that will execute the Promptbook
+const promptbookExecutor = createPromptbookExecutor({ promptbook, tools });
+
+// ▶ Prepare input parameters
+const inputParameters = { word: 'rabbit' };
+
+// 🚀▶ Execute the Promptbook
+const result = await promptbookExecutor(inputParameters);
+
+// ▶ Fail if the execution was not successful
+assertsExecutionSuccessful(result);
+
+// ▶ Handle the result
+const { isSuccessful, errors, outputParameters, executionReport } = result;
+console.info(outputParameters);
+```
+
+## 💕 Usage of multiple LLM providers
+
+You can use multiple LLM providers in one Promptbook execution. The best model will be chosen automatically according to the prompt and the model's capabilities.
+
+```typescript
+import {
+    createPromptbookExecutor,
+    createPromptbookLibraryFromDirectory,
+    assertsExecutionSuccessful,
+} from '@promptbook/core';
+import { JavascriptExecutionTools } from '@promptbook/execute-javascript';
+import { OpenAiExecutionTools } from '@promptbook/openai';
+
+// ▶ Create whole Promptbook library
+const library = await createPromptbookLibraryFromDirectory('./promptbook-library');
+
+// ▶ Get one Promptbook
+const promptbook = await library.getPromptbookByUrl(`https://promptbook.studio/my-library/write-article.ptbk.md`);
+
+// ▶ Prepare tools
+const tools = new MultipleLlmExecutionTools(
+    // Note: You can use multiple LLM providers in one Promptbook execution. The best model will be chosen automatically according to the prompt and the model's capabilities.
+    new AnthropicClaudeExecutionTools({
+        apiKey: process.env.ANTHROPIC_CLAUDE_API_KEY,
+    }),
+    new OpenAiExecutionTools({
+        apiKey: process.env.OPENAI_API_KEY,
+    }),
+    new AzureOpenAiExecutionTools({
+        resourceName: process.env.AZUREOPENAI_RESOURCE_NAME,
+        deploymentName: process.env.AZUREOPENAI_DEPLOYMENT_NAME,
+        apiKey: process.env.AZUREOPENAI_API_KEY,
+    }),
+);
+
+// ▶ Create executor - the function that will execute the Promptbook
+const promptbookExecutor = createPromptbookExecutor({ promptbook, tools });
+
+// ▶ Prepare input parameters
+const inputParameters = { word: 'bunny' };
+
+// 🚀▶ Execute the Promptbook
+const result = await promptbookExecutor(inputParameters);
+
+// ▶ Fail if the execution was not successful
+assertsExecutionSuccessful(result);
+
+// ▶ Handle the result
+const { isSuccessful, errors, outputParameters, executionReport } = result;
+console.info(outputParameters);
+```
+
 ## 💙 Integration with other models
@@ -41,0 +132,0 @@

umd/typings/execution/plugins/llm-execution-tools/remote/startRemoteServer.d.ts

@@ -13,2 +13,3 @@ import type { IDestroyable } from 'destroyable';
 /**
+ * TODO: [⚖] Expose the library to be able to connect to same library via createPromptbookLibraryFromUrl
  * TODO: Handle progress - support streaming
@@ -15,0 +16,0 @@ * TODO: [🤹‍♂️] Do not hang up immediately but wait until client closes OR timeout

umd/typings/library/constructors/createPromptbookLibraryFromUrl.d.ts

@@ -28,3 +28,4 @@ import { string_url } from '../../types/typeAliases';
 /***
+ * TODO: [⚖] Compatible with remote server
  * TODO: [🍓][🚯] !!! Add to README and samples + maybe make `@promptbook/library` package
  */

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

477314

increased by0.8%

Lines of code

7990

increased by0.05%

Number of lines in readme file

815

increased by12.57%

No dependency changes