From da5cfc42e590249199f47487fd5f28a131c7b98c Mon Sep 17 00:00:00 2001
From: Marcus Schiesser <mail@marcusschiesser.de>
Date: Tue, 30 Jul 2024 17:19:32 +0200
Subject: [PATCH] fix: integrate with `create-llama` (#1088)
Co-authored-by: Alex Yang <himself65@outlook.com>
---
.changeset/soft-kiwis-protect.md | 5 +++++
.changeset/spotty-shoes-poke.md | 5 +++++
.../llamaindex/src/cloud/LlamaCloudRetriever.ts | 8 +++++---
.../src/engines/chat/ContextChatEngine.ts | 2 +-
.../llamaindex/src/indices/vectorStore/index.ts | 16 ++++++++++++----
packages/llamaindex/src/readers/PDFReader.ts | 4 ++++
packages/llamaindex/src/readers/type.ts | 3 +--
7 files changed, 33 insertions(+), 10 deletions(-)
create mode 100644 .changeset/soft-kiwis-protect.md
create mode 100644 .changeset/spotty-shoes-poke.md
diff --git a/.changeset/soft-kiwis-protect.md b/.changeset/soft-kiwis-protect.md
new file mode 100644
index 000000000..3b6715807
--- /dev/null
+++ b/.changeset/soft-kiwis-protect.md
@@ -0,0 +1,5 @@
+---
+"llamaindex": patch
+---
+
+Add metadatafilter options to retriever constructors
diff --git a/.changeset/spotty-shoes-poke.md b/.changeset/spotty-shoes-poke.md
new file mode 100644
index 000000000..77fd17019
--- /dev/null
+++ b/.changeset/spotty-shoes-poke.md
@@ -0,0 +1,5 @@
+---
+"llamaindex": patch
+---
+
+Fix system prompt not used in ContextChatEngine
diff --git a/packages/llamaindex/src/cloud/LlamaCloudRetriever.ts b/packages/llamaindex/src/cloud/LlamaCloudRetriever.ts
index 74f704139..0f63fdf56 100644
--- a/packages/llamaindex/src/cloud/LlamaCloudRetriever.ts
+++ b/packages/llamaindex/src/cloud/LlamaCloudRetriever.ts
@@ -15,8 +15,8 @@ import { initService } from "./utils.js";
export type CloudRetrieveParams = Omit<
RetrievalParams,
- "query" | "searchFilters" | "className" | "denseSimilarityTopK"
-> & { similarityTopK?: number };
+ "query" | "search_filters" | "dense_similarity_top_k"
+> & { similarityTopK?: number; filters?: MetadataFilters };
export class LlamaCloudRetriever implements BaseRetriever {
clientParams: ClientParams;
@@ -84,7 +84,9 @@ export class LlamaCloudRetriever implements BaseRetriever {
requestBody: {
...this.retrieveParams,
query: extractText(query),
- search_filters: preFilters as MetadataFilters,
+ search_filters:
+ this.retrieveParams.filters ?? (preFilters as MetadataFilters),
+ dense_similarity_top_k: this.retrieveParams.similarityTopK,
},
});
diff --git a/packages/llamaindex/src/engines/chat/ContextChatEngine.ts b/packages/llamaindex/src/engines/chat/ContextChatEngine.ts
index 5230981ea..792c31f45 100644
--- a/packages/llamaindex/src/engines/chat/ContextChatEngine.ts
+++ b/packages/llamaindex/src/engines/chat/ContextChatEngine.ts
@@ -126,7 +126,7 @@ export class ContextChatEngine extends PromptMixin implements ChatEngine {
if (!this.systemPrompt) return message;
return {
...message,
- content: this.systemPrompt.trim() + "\n" + message.content,
+ content: this.systemPrompt.trim() + "\n" + extractText(message.content),
};
}
}
diff --git a/packages/llamaindex/src/indices/vectorStore/index.ts b/packages/llamaindex/src/indices/vectorStore/index.ts
index c4902da99..3959a4678 100644
--- a/packages/llamaindex/src/indices/vectorStore/index.ts
+++ b/packages/llamaindex/src/indices/vectorStore/index.ts
@@ -386,6 +386,7 @@ export type VectorIndexRetrieverOptions = {
index: VectorStoreIndex;
similarityTopK?: number;
topK?: TopKMap;
+ filters?: MetadataFilters;
};
export class VectorIndexRetriever implements BaseRetriever {
@@ -393,14 +394,21 @@ export class VectorIndexRetriever implements BaseRetriever {
topK: TopKMap;
serviceContext?: ServiceContext;
-
- constructor({ index, similarityTopK, topK }: VectorIndexRetrieverOptions) {
+ filters?: MetadataFilters;
+
+ constructor({
+ index,
+ similarityTopK,
+ topK,
+ filters,
+ }: VectorIndexRetrieverOptions) {
this.index = index;
this.serviceContext = this.index.serviceContext;
this.topK = topK ?? {
[ModalityType.TEXT]: similarityTopK ?? DEFAULT_SIMILARITY_TOP_K,
[ModalityType.IMAGE]: DEFAULT_SIMILARITY_TOP_K,
};
+ this.filters = filters;
}
/**
@@ -443,7 +451,7 @@ export class VectorIndexRetriever implements BaseRetriever {
query: MessageContent,
type: ModalityType,
vectorStore: VectorStore,
- preFilters?: MetadataFilters,
+ filters?: MetadataFilters,
): Promise<NodeWithScore[]> {
// convert string message to multi-modal format
if (typeof query === "string") {
@@ -460,7 +468,7 @@ export class VectorIndexRetriever implements BaseRetriever {
queryEmbedding,
mode: VectorStoreQueryMode.DEFAULT,
similarityTopK: this.topK[type],
- filters: preFilters ?? undefined,
+ filters: this.filters ?? filters ?? undefined,
});
nodes = nodes.concat(this.buildNodeListFromQueryResult(result));
}
diff --git a/packages/llamaindex/src/readers/PDFReader.ts b/packages/llamaindex/src/readers/PDFReader.ts
index 12f11cc31..3e5e3e448 100644
--- a/packages/llamaindex/src/readers/PDFReader.ts
+++ b/packages/llamaindex/src/readers/PDFReader.ts
@@ -6,6 +6,10 @@ import { FileReader } from "./type.js";
*/
export class PDFReader extends FileReader {
async loadDataAsContent(content: Uint8Array): Promise<Document[]> {
+ // XXX: create a new Uint8Array to prevent "Please provide binary data as `Uint8Array`, rather than `Buffer`." error if a Buffer passed
+ if (content instanceof Buffer) {
+ content = new Uint8Array(content);
+ }
const { totalPages, text } = await readPDF(content);
return text.map((text, page) => {
const metadata = {
diff --git a/packages/llamaindex/src/readers/type.ts b/packages/llamaindex/src/readers/type.ts
index bbaa6f3dd..80fe584e9 100644
--- a/packages/llamaindex/src/readers/type.ts
+++ b/packages/llamaindex/src/readers/type.ts
@@ -18,8 +18,7 @@ export abstract class FileReader implements BaseReader {
): Promise<Document[]>;
async loadData(filePath: string): Promise<Document[]> {
- // XXX: create a new Uint8Array to prevent "Please provide binary data as `Uint8Array`, rather than `Buffer`." error in PDFReader
- const fileContent = new Uint8Array(await fs.readFile(filePath));
+ const fileContent = await fs.readFile(filePath);
const fileName = path.basename(filePath);
const docs = await this.loadDataAsContent(fileContent, fileName);
docs.forEach(FileReader.addMetaData(filePath));
--
GitLab