diff --git a/documentloaders/ms_office.go b/documentloaders/ms_office.go
new file mode 100644
index 000000000..265598c29
--- /dev/null
+++ b/documentloaders/ms_office.go
@@ -0,0 +1,228 @@
+package documentloaders
+
+import (
+	"archive/zip"
+	"bytes"
+	"context"
+	"fmt"
+	"io"
+	"path/filepath"
+	"strings"
+
+	"github.com/richardlehane/mscfb"
+	"github.com/tealeg/xlsx"
+	"github.com/tmc/langchaingo/schema"
+	"github.com/tmc/langchaingo/textsplitter"
+)
+
+var _ Loader = Office{}
+
+// Office loads text data from an io.Reader.
+type Office struct {
+	reader   io.ReaderAt
+	size     int64
+	fileType string
+}
+
+// NewOffice creates a new text loader with an io.Reader, filename and file size.
+func NewOffice(reader io.ReaderAt, filename string, size int64) Office {
+	return Office{
+		reader:   reader,
+		size:     size,
+		fileType: strings.ToLower(filepath.Ext(filename)),
+	}
+}
+
+// Load reads from the io.Reader for the MS Office data and returns the raw document data.
+// nolint
+func (loader Office) Load(ctx context.Context) ([]schema.Document, error) {
+	switch loader.fileType {
+	case ".doc":
+		return loader.loadDoc()
+	case ".docx":
+		return loader.loadDocx()
+	case ".xls", ".xlsx":
+		return loader.loadExcel()
+	case ".ppt":
+		// parsing for old PPTs is same as for old DOCs
+		return loader.loadDoc()
+	case ".pptx":
+		return loader.loadPPTX()
+	default:
+		return nil, fmt.Errorf("unsupported file type: %s", loader.fileType)
+	}
+}
+
+// LoadAndSplit reads from the io.Reader for the MS Office data and returns the raw document data
+// and splits it into multiple documents using a text splitter.
+func (loader Office) LoadAndSplit(ctx context.Context, splitter textsplitter.TextSplitter) ([]schema.Document, error) {
+	docs, err := loader.Load(ctx)
+	if err != nil {
+		return nil, err
+	}
+
+	return textsplitter.SplitDocuments(splitter, docs)
+}
+
+func (loader Office) loadDoc() ([]schema.Document, error) {
+	doc, err := mscfb.New(io.NewSectionReader(loader.reader, 0, loader.size))
+	if err != nil {
+		return nil, fmt.Errorf("failed to read DOC file: %w", err)
+	}
+
+	var text strings.Builder
+	for entry, err := doc.Next(); err == nil; entry, err = doc.Next() {
+		// nolint
+		if entry.Name == "WordDocument" {
+			buf := make([]byte, entry.Size)
+			i, err := doc.Read(buf)
+			if err != nil {
+				return nil, fmt.Errorf("error reading WordDocument stream: %w", err)
+			}
+			if i > 0 {
+				// Process the binary content
+				for j := 0; j < i; j++ {
+					// Extract readable ASCII text
+					if buf[j] >= 32 && buf[j] <= 126 {
+						text.WriteByte(buf[j])
+					} else if buf[j] == 13 || buf[j] == 10 {
+						text.WriteByte('\n')
+					}
+				}
+			}
+		}
+	}
+
+	documents := []schema.Document{
+		{
+			PageContent: text.String(),
+			Metadata: map[string]interface{}{
+				"fileType": loader.fileType,
+			},
+		},
+	}
+
+	return documents, nil
+}
+
+func (loader Office) loadExcel() ([]schema.Document, error) {
+	buf := bytes.NewBuffer(make([]byte, 0, loader.size))
+	if _, err := io.Copy(buf, io.NewSectionReader(loader.reader, 0, loader.size)); err != nil {
+		return nil, fmt.Errorf("failed to copy Excel content: %w", err)
+	}
+
+	xlFile, err := xlsx.OpenBinary(buf.Bytes())
+	if err != nil {
+		return nil, fmt.Errorf("failed to read Excel file: %w", err)
+	}
+
+	docs := make([]schema.Document, 0, len(xlFile.Sheets))
+	for i, sheet := range xlFile.Sheets {
+		var text strings.Builder
+		for _, row := range sheet.Rows {
+			for _, cell := range row.Cells {
+				text.WriteString(cell.String() + "\t")
+			}
+			text.WriteString("\n")
+		}
+
+		docs = append(docs, schema.Document{
+			PageContent: text.String(),
+			Metadata: map[string]interface{}{
+				"fileType":   loader.fileType,
+				"sheetName":  sheet.Name,
+				"sheetIndex": i,
+			},
+		})
+	}
+
+	return docs, nil
+}
+
+func (loader Office) loadPPTX() ([]schema.Document, error) {
+	buf := bytes.NewBuffer(make([]byte, 0, loader.size))
+	if _, err := io.Copy(buf, io.NewSectionReader(loader.reader, 0, loader.size)); err != nil {
+		return nil, fmt.Errorf("failed to copy content: %w", err)
+	}
+
+	zipReader, err := zip.NewReader(bytes.NewReader(buf.Bytes()), loader.size)
+	if err != nil {
+		return nil, fmt.Errorf("failed to read PPTX file as ZIP: %w", err)
+	}
+
+	var text strings.Builder
+	for _, file := range zipReader.File {
+		// PPTX stores slide content in ppt/slides/slide*.xml files
+		if strings.HasPrefix(file.Name, "ppt/slides/slide") && strings.HasSuffix(file.Name, ".xml") {
+			rc, err := file.Open()
+			if err != nil {
+				return nil, fmt.Errorf("error opening slide XML: %w", err)
+			}
+			defer rc.Close()
+
+			content, err := io.ReadAll(rc)
+			if err != nil {
+				return nil, fmt.Errorf("error reading content: %w", err)
+			}
+
+			content = bytes.ReplaceAll(content, []byte("<"), []byte(" <"))
+			content = bytes.ReplaceAll(content, []byte(">"), []byte("> "))
+			text.Write(content)
+			text.WriteString("\n--- Next Slide ---\n")
+		}
+	}
+
+	documents := []schema.Document{
+		{
+			PageContent: text.String(),
+			Metadata: map[string]interface{}{
+				"fileType": loader.fileType,
+			},
+		},
+	}
+
+	return documents, nil
+}
+
+func (loader Office) loadDocx() ([]schema.Document, error) {
+	buf := bytes.NewBuffer(make([]byte, 0, loader.size))
+	if _, err := io.Copy(buf, io.NewSectionReader(loader.reader, 0, loader.size)); err != nil {
+		return nil, fmt.Errorf("failed to copy content: %w", err)
+	}
+
+	zipReader, err := zip.NewReader(bytes.NewReader(buf.Bytes()), loader.size)
+	if err != nil {
+		return nil, fmt.Errorf("failed to read DOCX file as ZIP: %w", err)
+	}
+
+	var text strings.Builder
+	for _, file := range zipReader.File {
+		if file.Name == "word/document.xml" {
+			rc, err := file.Open()
+			if err != nil {
+				return nil, fmt.Errorf("error opening document.xml: %w", err)
+			}
+			defer rc.Close()
+
+			content, err := io.ReadAll(rc)
+			if err != nil {
+				return nil, fmt.Errorf("error reading content: %w", err)
+			}
+
+			content = bytes.ReplaceAll(content, []byte("<"), []byte(" <"))
+			content = bytes.ReplaceAll(content, []byte(">"), []byte("> "))
+			text.Write(content)
+		}
+	}
+
+	documents := []schema.Document{
+		{
+			PageContent: text.String(),
+			Metadata: map[string]interface{}{
+				"fileType": loader.fileType,
+			},
+		},
+	}
+
+	return documents, nil
+}
diff --git a/documentloaders/ms_office_test.go b/documentloaders/ms_office_test.go
new file mode 100644
index 000000000..b85873a7b
--- /dev/null
+++ b/documentloaders/ms_office_test.go
@@ -0,0 +1,92 @@
+package documentloaders
+
+import (
+	"context"
+	"os"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestMSOfficeLoader(test *testing.T) {
+	test.Parallel()
+
+	docExpectedContent := "This is a .doc test file."
+	docxExpectedContent := "This is a .docx test file."
+	xlsxExpectedContent := "This is an .xlsx test file"
+	pptxExpectedContent := "This is a .pptx test file"
+
+	test.Run("Load .doc", func(t *testing.T) {
+		t.Parallel()
+
+		file, err := os.Open("./testdata/test.doc")
+		require.NoError(t, err)
+		defer file.Close()
+
+		fileInfo, err := file.Stat()
+		require.NoError(t, err)
+
+		loader := NewOffice(file, fileInfo.Name(), fileInfo.Size())
+		docs, err := loader.Load(context.Background())
+		require.NoError(t, err)
+
+		assert.Len(t, docs, 1)
+		assert.True(t, strings.Contains(docs[0].PageContent, docExpectedContent))
+	})
+
+	test.Run("Load .docx", func(t *testing.T) {
+		t.Parallel()
+
+		file, err := os.Open("./testdata/test.docx")
+		require.NoError(t, err)
+		defer file.Close()
+
+		fileInfo, err := file.Stat()
+		require.NoError(t, err)
+
+		loader := NewOffice(file, fileInfo.Name(), fileInfo.Size())
+		docs, err := loader.Load(context.Background())
+		require.NoError(t, err)
+
+		assert.Len(t, docs, 1)
+		assert.True(t, strings.Contains(docs[0].PageContent, docxExpectedContent))
+	})
+
+	test.Run("Load .xlsx", func(t *testing.T) {
+		t.Parallel()
+
+		file, err := os.Open("./testdata/test.xlsx")
+		require.NoError(t, err)
+		defer file.Close()
+
+		fileInfo, err := file.Stat()
+		require.NoError(t, err)
+
+		loader := NewOffice(file, fileInfo.Name(), fileInfo.Size())
+		docs, err := loader.Load(context.Background())
+		require.NoError(t, err)
+
+		assert.Len(t, docs, 1)
+		assert.True(t, strings.Contains(docs[0].PageContent, xlsxExpectedContent))
+	})
+
+	test.Run("Load .pptx", func(t *testing.T) {
+		t.Parallel()
+
+		file, err := os.Open("./testdata/test.pptx")
+		require.NoError(t, err)
+		defer file.Close()
+
+		fileInfo, err := file.Stat()
+		require.NoError(t, err)
+
+		loader := NewOffice(file, fileInfo.Name(), fileInfo.Size())
+		docs, err := loader.Load(context.Background())
+		require.NoError(t, err)
+
+		assert.Len(t, docs, 1)
+		assert.True(t, strings.Contains(docs[0].PageContent, pptxExpectedContent))
+	})
+}
diff --git a/documentloaders/testdata/test.doc b/documentloaders/testdata/test.doc
new file mode 100644
index 000000000..7a02661d4
Binary files /dev/null and b/documentloaders/testdata/test.doc differ
diff --git a/documentloaders/testdata/test.docx b/documentloaders/testdata/test.docx
new file mode 100644
index 000000000..65858f722
Binary files /dev/null and b/documentloaders/testdata/test.docx differ
diff --git a/documentloaders/testdata/test.pptx b/documentloaders/testdata/test.pptx
new file mode 100644
index 000000000..151caafa8
Binary files /dev/null and b/documentloaders/testdata/test.pptx differ
diff --git a/documentloaders/testdata/test.xlsx b/documentloaders/testdata/test.xlsx
new file mode 100644
index 000000000..8f9f5afc1
Binary files /dev/null and b/documentloaders/testdata/test.xlsx differ
diff --git a/go.mod b/go.mod
index f3270f4c2..d34a4b3fa 100644
--- a/go.mod
+++ b/go.mod
@@ -134,6 +134,7 @@ require (
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c // indirect
+	github.com/richardlehane/msoleps v1.0.1 // indirect
 	github.com/rogpeppe/go-internal v1.11.0 // indirect
 	github.com/rs/zerolog v1.31.0 // indirect
 	github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d // indirect
@@ -158,7 +159,6 @@ require (
 	gitlab.com/golang-commonmark/linkify v0.0.0-20191026162114-a0c2df6c8f82 // indirect
 	gitlab.com/golang-commonmark/mdurl v0.0.0-20191124015652-932350d1cb84 // indirect
 	gitlab.com/golang-commonmark/puny v0.0.0-20191124015043-9f83538fa04f // indirect
-	go.mongodb.org/mongo-driver/v2 v2.0.0-beta1 // indirect
 	go.opencensus.io v0.24.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.51.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.51.0 // indirect
@@ -216,10 +216,13 @@ require (
 	github.com/pinecone-io/go-pinecone v0.4.1
 	github.com/pkoukk/tiktoken-go v0.1.6
 	github.com/redis/rueidis v1.0.34
+	github.com/richardlehane/mscfb v1.0.4
+	github.com/tealeg/xlsx v1.0.5
 	github.com/weaviate/weaviate v1.24.1
 	github.com/weaviate/weaviate-go-client/v4 v4.13.1
 	gitlab.com/golang-commonmark/markdown v0.0.0-20211110145824-bf3e522c626a
 	go.mongodb.org/mongo-driver v1.14.0
+	go.mongodb.org/mongo-driver/v2 v2.0.0-beta1
 	go.starlark.net v0.0.0-20230302034142-4b1e35fe2254
 	golang.org/x/exp v0.0.0-20230713183714-613f0c0eb8a1
 	golang.org/x/tools v0.14.0
diff --git a/go.sum b/go.sum
index 1579d1c52..41eb8bccc 100644
--- a/go.sum
+++ b/go.sum
@@ -602,6 +602,10 @@ github.com/qdrant/go-client v1.7.0 h1:2TeeWyZAWIup7vvD7Ne6aAvo0H+F5OUb1pB9Z8Y4pF
 github.com/qdrant/go-client v1.7.0/go.mod h1:680gkxNAsVtre0Z8hAQmtPzJtz1xFAyCu2TUxULtnoE=
 github.com/redis/rueidis v1.0.34 h1:cdggTaDDoqLNeoKMoew8NQY3eTc83Kt6XyfXtoCO2Wc=
 github.com/redis/rueidis v1.0.34/go.mod h1:g8nPmgR4C68N3abFiOc/gUOSEKw3Tom6/teYMehg4RE=
+github.com/richardlehane/mscfb v1.0.4 h1:WULscsljNPConisD5hR0+OyZjwK46Pfyr6mPu5ZawpM=
+github.com/richardlehane/mscfb v1.0.4/go.mod h1:YzVpcZg9czvAuhk9T+a3avCpcFPMUWm7gK3DypaEsUk=
+github.com/richardlehane/msoleps v1.0.1 h1:RfrALnSNXzmXLbGct/P2b4xkFz4e8Gmj/0Vj9M9xC1o=
+github.com/richardlehane/msoleps v1.0.1/go.mod h1:BWev5JBpU9Ko2WAgmZEuiz4/u3ZYTKbjLycmwiWUfWg=
 github.com/rogpeppe/go-internal v1.1.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
 github.com/rogpeppe/go-internal v1.2.2/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
 github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
@@ -668,6 +672,8 @@ github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/tealeg/xlsx v1.0.5 h1:+f8oFmvY8Gw1iUXzPk+kz+4GpbDZPK1FhPiQRd+ypgE=
+github.com/tealeg/xlsx v1.0.5/go.mod h1:btRS8dz54TDnvKNosuAqxrM1QgN1udgk9O34bDCnORM=
 github.com/temoto/robotstxt v1.1.2 h1:W2pOjSJ6SWvldyEuiFXNxz3xZ8aiWX5LbfDiOFd7Fxg=
 github.com/temoto/robotstxt v1.1.2/go.mod h1:+1AmkuG3IYkh1kv0d2qEB9Le88ehNO0zwOr3ujewlOo=
 github.com/testcontainers/testcontainers-go v0.31.0 h1:W0VwIhcEVhRflwL9as3dhY6jXjVCA27AkmbnZ+UTh3U=