From 553bc55b1980a6d2d579f32d51ff9c7b7bd477e7 Mon Sep 17 00:00:00 2001
From: Alex Yang <himself65@outlook.com>
Date: Mon, 9 Sep 2024 10:15:21 -0700
Subject: [PATCH] refactor: move `PromptHelper` into core package (#1166)
---
packages/core/package.json | 14 ++++++
packages/core/src/indices/index.ts | 5 ++
.../src/indices/prompt-helper.ts} | 46 ++++++++++++-------
packages/llamaindex/src/ServiceContext.ts | 2 +-
packages/llamaindex/src/Settings.ts | 2 +-
packages/llamaindex/src/index.edge.ts | 2 +-
.../llamaindex/src/synthesizers/builders.ts | 2 +-
7 files changed, 53 insertions(+), 20 deletions(-)
create mode 100644 packages/core/src/indices/index.ts
rename packages/{llamaindex/src/PromptHelper.ts => core/src/indices/prompt-helper.ts} (79%)
diff --git a/packages/core/package.json b/packages/core/package.json
index 54fcef067..d1bd24cd5 100644
--- a/packages/core/package.json
+++ b/packages/core/package.json
@@ -129,6 +129,20 @@
"types": "./dist/prompts/index.d.ts",
"default": "./dist/prompts/index.js"
}
+ },
+ "./indices": {
+ "require": {
+ "types": "./dist/indices/index.d.cts",
+ "default": "./dist/indices/index.cjs"
+ },
+ "import": {
+ "types": "./dist/indices/index.d.ts",
+ "default": "./dist/indices/index.js"
+ },
+ "default": {
+ "types": "./dist/indices/index.d.ts",
+ "default": "./dist/indices/index.js"
+ }
}
},
"files": [
diff --git a/packages/core/src/indices/index.ts b/packages/core/src/indices/index.ts
new file mode 100644
index 000000000..5545c65aa
--- /dev/null
+++ b/packages/core/src/indices/index.ts
@@ -0,0 +1,5 @@
+export {
+ PromptHelper,
+ getBiggestPrompt,
+ type PromptHelperOptions,
+} from "./prompt-helper";
diff --git a/packages/llamaindex/src/PromptHelper.ts b/packages/core/src/indices/prompt-helper.ts
similarity index 79%
rename from packages/llamaindex/src/PromptHelper.ts
rename to packages/core/src/indices/prompt-helper.ts
index c4618ecde..473885efd 100644
--- a/packages/llamaindex/src/PromptHelper.ts
+++ b/packages/core/src/indices/prompt-helper.ts
@@ -1,17 +1,17 @@
+import { type Tokenizer, tokenizers } from "@llamaindex/env";
import {
DEFAULT_CHUNK_OVERLAP_RATIO,
DEFAULT_CONTEXT_WINDOW,
DEFAULT_NUM_OUTPUTS,
DEFAULT_PADDING,
-} from "@llamaindex/core/global";
-import { SentenceSplitter } from "@llamaindex/core/node-parser";
-import type { PromptTemplate } from "@llamaindex/core/prompts";
-import { type Tokenizer, tokenizers } from "@llamaindex/env";
+} from "../global";
+import { SentenceSplitter } from "../node-parser";
+import type { PromptTemplate } from "../prompts";
/**
* Get the empty prompt text given a prompt.
*/
-export function getEmptyPromptTxt(prompt: PromptTemplate) {
+function getEmptyPromptTxt(prompt: PromptTemplate) {
return prompt.format({
...Object.fromEntries(
[...prompt.templateVars.keys()].map((key) => [key, ""]),
@@ -31,6 +31,15 @@ export function getBiggestPrompt(prompts: PromptTemplate[]) {
return prompts[maxEmptyPromptIndex];
}
+export type PromptHelperOptions = {
+ contextWindow?: number;
+ numOutput?: number;
+ chunkOverlapRatio?: number;
+ chunkSizeLimit?: number;
+ tokenizer?: Tokenizer;
+ separator?: string;
+};
+
/**
* A collection of helper functions for working with prompts.
*/
@@ -42,15 +51,15 @@ export class PromptHelper {
tokenizer: Tokenizer;
separator = " ";
- // eslint-disable-next-line max-params
- constructor(
- contextWindow = DEFAULT_CONTEXT_WINDOW,
- numOutput = DEFAULT_NUM_OUTPUTS,
- chunkOverlapRatio = DEFAULT_CHUNK_OVERLAP_RATIO,
- chunkSizeLimit?: number,
- tokenizer?: Tokenizer,
- separator = " ",
- ) {
+ constructor(options: PromptHelperOptions = {}) {
+ const {
+ contextWindow = DEFAULT_CONTEXT_WINDOW,
+ numOutput = DEFAULT_NUM_OUTPUTS,
+ chunkOverlapRatio = DEFAULT_CHUNK_OVERLAP_RATIO,
+ chunkSizeLimit,
+ tokenizer,
+ separator = " ",
+ } = options;
this.contextWindow = contextWindow;
this.numOutput = numOutput;
this.chunkOverlapRatio = chunkOverlapRatio;
@@ -79,7 +88,7 @@ export class PromptHelper {
prompt: PromptTemplate,
numChunks = 1,
padding = 5,
- ) {
+ ): number {
const availableContextSize = this.getAvailableContextSize(prompt);
const result = Math.floor(availableContextSize / numChunks) - padding;
@@ -104,7 +113,12 @@ export class PromptHelper {
throw new Error("Got 0 as available chunk size");
}
const chunkOverlap = this.chunkOverlapRatio * chunkSize;
- return new SentenceSplitter({ chunkSize, chunkOverlap });
+ return new SentenceSplitter({
+ chunkSize,
+ chunkOverlap,
+ separator: this.separator,
+ tokenizer: this.tokenizer,
+ });
}
/**
diff --git a/packages/llamaindex/src/ServiceContext.ts b/packages/llamaindex/src/ServiceContext.ts
index 8cb24c94c..c6c1885f2 100644
--- a/packages/llamaindex/src/ServiceContext.ts
+++ b/packages/llamaindex/src/ServiceContext.ts
@@ -1,10 +1,10 @@
import type { BaseEmbedding } from "@llamaindex/core/embeddings";
+import { PromptHelper } from "@llamaindex/core/indices";
import type { LLM } from "@llamaindex/core/llms";
import {
type NodeParser,
SentenceSplitter,
} from "@llamaindex/core/node-parser";
-import { PromptHelper } from "./PromptHelper.js";
import { OpenAIEmbedding } from "./embeddings/OpenAIEmbedding.js";
import { OpenAI } from "./llm/openai.js";
diff --git a/packages/llamaindex/src/Settings.ts b/packages/llamaindex/src/Settings.ts
index 0fb712d6c..778a6fee4 100644
--- a/packages/llamaindex/src/Settings.ts
+++ b/packages/llamaindex/src/Settings.ts
@@ -4,7 +4,7 @@ import {
} from "@llamaindex/core/global";
import { OpenAI } from "./llm/openai.js";
-import { PromptHelper } from "./PromptHelper.js";
+import { PromptHelper } from "@llamaindex/core/indices";
import type { BaseEmbedding } from "@llamaindex/core/embeddings";
import type { LLM } from "@llamaindex/core/llms";
diff --git a/packages/llamaindex/src/index.edge.ts b/packages/llamaindex/src/index.edge.ts
index 869087245..b23086cd5 100644
--- a/packages/llamaindex/src/index.edge.ts
+++ b/packages/llamaindex/src/index.edge.ts
@@ -30,6 +30,7 @@ export type {
LLMToolCallEvent,
LLMToolResultEvent,
} from "@llamaindex/core/global";
+export * from "@llamaindex/core/indices";
export * from "@llamaindex/core/llms";
export * from "@llamaindex/core/prompts";
export * from "@llamaindex/core/schema";
@@ -62,7 +63,6 @@ export * from "./nodeParsers/index.js";
export * from "./objects/index.js";
export * from "./OutputParser.js";
export * from "./postprocessors/index.js";
-export * from "./PromptHelper.js";
export * from "./QuestionGenerator.js";
export * from "./Retriever.js";
export * from "./selectors/index.js";
diff --git a/packages/llamaindex/src/synthesizers/builders.ts b/packages/llamaindex/src/synthesizers/builders.ts
index f5abc2335..b8709bd28 100644
--- a/packages/llamaindex/src/synthesizers/builders.ts
+++ b/packages/llamaindex/src/synthesizers/builders.ts
@@ -1,3 +1,4 @@
+import { getBiggestPrompt, type PromptHelper } from "@llamaindex/core/indices";
import type { LLM } from "@llamaindex/core/llms";
import {
PromptMixin,
@@ -12,7 +13,6 @@ import {
} from "@llamaindex/core/prompts";
import type { QueryType } from "@llamaindex/core/query-engine";
import { extractText, streamConverter } from "@llamaindex/core/utils";
-import { getBiggestPrompt, type PromptHelper } from "../PromptHelper.js";
import type { ServiceContext } from "../ServiceContext.js";
import {
llmFromSettingsOrContext,
--
GitLab