@mastra/pg 1.2.0 → 1.3.0-alpha.0

package/dist/docs/{rag/03-retrieval.md → references/docs-rag-retrieval.md}

@@ -1,5 +1,3 @@
-> Guide on retrieval processes in Mastra
-
 # Retrieval in RAG Systems
 
 After storing embeddings, you need to retrieve relevant chunks to answer user queries.
@@ -168,10 +166,9 @@ This is particularly useful when:
 
 The Vector Query Tool supports database-specific configurations that enable you to leverage unique features and optimizations of different vector stores.
 
-> **Note:**
-These configurations are for **query-time options** like namespaces, performance tuning, and filtering—not for database connection setup. 
-
-Connection credentials (URLs, auth tokens) are configured when you instantiate the vector store class (e.g., `new LibSQLVector({ url: '...' })`).
+> **Note:** These configurations are for **query-time options** like namespaces, performance tuning, and filtering—not for database connection setup.
+>
+> Connection credentials (URLs, auth tokens) are configured when you instantiate the vector store class (e.g., `new LibSQLVector({ url: '...' })`).
 
 ```ts
 import { createVectorQueryTool } from "@mastra/rag";
@@ -268,10 +265,9 @@ For detailed configuration options and advanced usage, see the [Vector Query Too
 
 ### Vector Store Prompts
 
-Vector store prompts define query patterns and filtering capabilities for each vector database implementation.
-When implementing filtering, these prompts are required in the agent's instructions to specify valid operators and syntax for each vector store implementation.
+Vector store prompts define query patterns and filtering capabilities for each vector database implementation. When implementing filtering, these prompts are required in the agent's instructions to specify valid operators and syntax for each vector store implementation.
 
-  **pgvector:**
+**pgVector**:
 
 ```ts
 import { PGVECTOR_PROMPT } from "@mastra/pg";
@@ -288,11 +284,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
-
-  **pinecone:**
+**Pinecone**:
 
-```ts title="vector-store.ts"
+```ts
 import { PINECONE_PROMPT } from "@mastra/pinecone";
 
 export const ragAgent = new Agent({
@@ -307,11 +301,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
-
-  **qdrant:**
+**Qdrant**:
 
-```ts title="vector-store.ts"
+```ts
 import { QDRANT_PROMPT } from "@mastra/qdrant";
 
 export const ragAgent = new Agent({
@@ -326,11 +318,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
+**Chroma**:
 
-  **chroma:**
-
-```ts title="vector-store.ts"
+```ts
 import { CHROMA_PROMPT } from "@mastra/chroma";
 
 export const ragAgent = new Agent({
@@ -345,11 +335,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
-
-  **astra:**
+**Astra**:
 
-```ts title="vector-store.ts"
+```ts
 import { ASTRA_PROMPT } from "@mastra/astra";
 
 export const ragAgent = new Agent({
@@ -364,11 +352,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
-
-  **libsql:**
+**libSQL**:
 
-```ts title="vector-store.ts"
+```ts
 import { LIBSQL_PROMPT } from "@mastra/libsql";
 
 export const ragAgent = new Agent({
@@ -383,11 +369,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
+**Upstash**:
 
-  **upstash:**
-
-```ts title="vector-store.ts"
+```ts
 import { UPSTASH_PROMPT } from "@mastra/upstash";
 
 export const ragAgent = new Agent({
@@ -402,11 +386,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
-
-  **vectorize:**
+**Vectorize**:
 
-```ts title="vector-store.ts"
+```ts
 import { VECTORIZE_PROMPT } from "@mastra/vectorize";
 
 export const ragAgent = new Agent({
@@ -421,11 +403,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
-
-  **mongodb:**
+**MongoDB**:
 
-```ts title="vector-store.ts"
+```ts
 import { MONGODB_PROMPT } from "@mastra/mongodb";
 
 export const ragAgent = new Agent({
@@ -440,11 +420,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
+**OpenSearch**:
 
-  **opensearch:**
-
-```ts title="vector-store.ts"
+```ts
 import { OPENSEARCH_PROMPT } from "@mastra/opensearch";
 
 export const ragAgent = new Agent({
@@ -459,11 +437,9 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
-
-  **s3vectors:**
+**S3Vectors**:
 
-```ts title="vector-store.ts"
+```ts
 import { S3VECTORS_PROMPT } from "@mastra/s3vectors";
 
 export const ragAgent = new Agent({
@@ -478,8 +454,6 @@ export const ragAgent = new Agent({
 });
 ```
 
-  
-
 ### Re-ranking
 
 Initial vector similarity search can sometimes miss nuanced relevance. Re-ranking is a more computationally expensive process, but more accurate algorithm that improves results by:
@@ -528,8 +502,7 @@ The weights control how different factors influence the final ranking:
 - `vector`: Higher values favor the original vector similarity scores
 - `position`: Higher values help maintain the original ordering of results
 
-> **Note:**
-For semantic scoring to work properly during re-ranking, each result must include the text content in its `metadata.text` field.
+> **Note:** For semantic scoring to work properly during re-ranking, each result must include the text content in its `metadata.text` field.
 
 You can also use other relevance score providers like Cohere or ZeroEntropy: