Compare commits

...

4 Commits

Author SHA1 Message Date
Alex Yang ddf07752d8 Merge branch 'main' into ms/fixes-for-cl 2024-07-30 08:00:20 -07:00
Marcus Schiesser 177aac766f fix: system prompt not used in ContextChatEngine 2024-07-30 15:50:29 +02:00
Marcus Schiesser 008edcf1d2 feat: Add metadatafilter options to retriever constructors 2024-07-30 15:50:29 +02:00
Marcus Schiesser 4b3bfc395b fix: PDFReader buffer error 2024-07-30 15:50:29 +02:00
7 changed files with 32 additions and 9 deletions
+5
View File
@@ -0,0 +1,5 @@
---
"llamaindex": patch
---
Add metadatafilter options to retriever constructors
+5
View File
@@ -0,0 +1,5 @@
---
"llamaindex": patch
---
Fix system prompt not used in ContextChatEngine
@@ -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,
},
});
@@ -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),
};
}
}
@@ -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;
filters?: MetadataFilters;
constructor({ index, similarityTopK, topK }: VectorIndexRetrieverOptions) {
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));
}
@@ -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 = {
+1 -2
View File
@@ -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));