Adjust chunk sizes for examples.

Author: badmonster0

README.md

@@ -63,7 +63,7 @@ def text_embedding_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoind
         # Split the document into chunks, put into `chunks` field
         doc["chunks"] = doc["content"].transform(
             cocoindex.functions.SplitRecursively(),
-            language="markdown", chunk_size=300, chunk_overlap=100)
+            language="markdown", chunk_size=2000, chunk_overlap=500)
 
         # Transform data of each chunk
         with doc["chunks"].row() as chunk:

docs/docs/getting_started/quickstart.md

@@ -79,7 +79,7 @@ def text_embedding_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoind
         # Split the document into chunks, put into `chunks` field
         doc["chunks"] = doc["content"].transform(
             cocoindex.functions.SplitRecursively(),
-            language="markdown", chunk_size=300, chunk_overlap=100)
+            language="markdown", chunk_size=2000, chunk_overlap=500)
 
         # Transform data of each chunk
         with doc["chunks"].row() as chunk:

examples/code_embedding/code_embedding.py

@@ -22,7 +22,7 @@ def code_embedding_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoind
     with data_scope["files"].row() as file:
         file["chunks"] = file["content"].transform(
             cocoindex.functions.SplitRecursively(),
-            language="javascript", chunk_size=300, chunk_overlap=100)
+            language="python", chunk_size=2000, chunk_overlap=500)
         with file["chunks"].row() as chunk:
             chunk["embedding"] = chunk["text"].call(code_to_embedding)
             code_embeddings.collect(filename=file["filename"], location=chunk["location"],

examples/pdf_embedding/pdf_embedding.py

@@ -51,7 +51,7 @@ def pdf_embedding_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoinde
         doc["markdown"] = doc["content"].transform(PdfToMarkdown())
         doc["chunks"] = doc["markdown"].transform(
             cocoindex.functions.SplitRecursively(),
-            language="markdown", chunk_size=300, chunk_overlap=100)
+            language="markdown", chunk_size=2000, chunk_overlap=500)
 
         with doc["chunks"].row() as chunk:
             chunk["embedding"] = chunk["text"].call(text_to_embedding)

examples/text_embedding/text_embedding.py

@@ -24,7 +24,7 @@ def text_embedding_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoind
     with data_scope["documents"].row() as doc:
         doc["chunks"] = doc["content"].transform(
             cocoindex.functions.SplitRecursively(),
-            language="markdown", chunk_size=300, chunk_overlap=100)
+            language="markdown", chunk_size=2000, chunk_overlap=500)
 
         with doc["chunks"].row() as chunk:
             chunk["embedding"] = text_to_embedding(chunk["text"])