From aab05388d5bcf315f31c01e9ce4c7995919ca23a Mon Sep 17 00:00:00 2001
From: Lorenze Jay <lorenzejaytech@gmail.com>
Date: Tue, 3 Dec 2024 10:12:37 -0800
Subject: [PATCH] fixed types

---
 docs/concepts/knowledge.mdx                   | 29 ++++++++++++++++---
 .../source/base_file_knowledge_source.py      |  3 ++
 .../source/excel_knowledge_source.py          |  4 +--
 .../knowledge/source/json_knowledge_source.py |  1 +
 .../source/text_file_knowledge_source.py      |  1 +
 5 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/docs/concepts/knowledge.mdx b/docs/concepts/knowledge.mdx
index 69fa4e644..a00b2c2f0 100644
--- a/docs/concepts/knowledge.mdx
+++ b/docs/concepts/knowledge.mdx
@@ -156,14 +156,35 @@ crew = Crew(
     agents=[agent],
     tasks=[task],
     knowledge_sources=[source],
-    embedder_config={
-        "model": "BAAI/bge-small-en-v1.5",
-        "normalize": True,
-        "max_length": 512
+    embedder={
+        "provider": "ollama",
+        "config": {"model": "nomic-embed-text:latest"},
     }
 )
 ```
 
+### Referencing Sources
+
+You can reference knowledge sources by their collection name or metadata.
+
+* Add a directory to your crew project called `knowledge`:
+* File paths in knowledge can be referenced relative to the `knowledge` directory.
+
+Example:
+A file inside the `knowledge` directory called `example.txt` can be referenced as `example.txt`.
+
+```python
+source = TextFileKnowledgeSource(
+    file_path="example.txt", # or /example.txt
+    collection_name="example"
+)
+crew = Crew(
+    agents=[agent],
+    tasks=[task],
+    knowledge_sources=[source],
+)
+```
+
 ## Best Practices
 
 <AccordionGroup>
diff --git a/src/crewai/knowledge/source/base_file_knowledge_source.py b/src/crewai/knowledge/source/base_file_knowledge_source.py
index ad160683d..ebb3341a8 100644
--- a/src/crewai/knowledge/source/base_file_knowledge_source.py
+++ b/src/crewai/knowledge/source/base_file_knowledge_source.py
@@ -37,6 +37,9 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource):
         if not isinstance(paths, list):
             raise ValueError("file_path must be a Path or a list of Paths")
 
+        # Ensure all paths are Path objects
+        paths = [Path(path) if isinstance(path, str) else path for path in paths]
+
         for path in paths:
             if not path.exists():
                 self._logger.log(
diff --git a/src/crewai/knowledge/source/excel_knowledge_source.py b/src/crewai/knowledge/source/excel_knowledge_source.py
index 3b5c71514..50520b668 100644
--- a/src/crewai/knowledge/source/excel_knowledge_source.py
+++ b/src/crewai/knowledge/source/excel_knowledge_source.py
@@ -12,9 +12,9 @@ class ExcelKnowledgeSource(BaseFileKnowledgeSource):
         pd = self._import_dependencies()
 
         if isinstance(self.file_path, list):
-            file_path = self.file_path[0]
+            file_path = self.convert_to_path(self.file_path[0])
         else:
-            file_path = self.file_path
+            file_path = self.convert_to_path(self.file_path)
 
         df = pd.read_excel(file_path)
         content = df.to_csv(index=False)
diff --git a/src/crewai/knowledge/source/json_knowledge_source.py b/src/crewai/knowledge/source/json_knowledge_source.py
index 490423a00..e899bb338 100644
--- a/src/crewai/knowledge/source/json_knowledge_source.py
+++ b/src/crewai/knowledge/source/json_knowledge_source.py
@@ -15,6 +15,7 @@ class JSONKnowledgeSource(BaseFileKnowledgeSource):
 
         content: Dict[Path, str] = {}
         for path in paths:
+            path = self.convert_to_path(path)
             with open(path, "r", encoding="utf-8") as json_file:
                 data = json.load(json_file)
             content[path] = self._json_to_text(data)
diff --git a/src/crewai/knowledge/source/text_file_knowledge_source.py b/src/crewai/knowledge/source/text_file_knowledge_source.py
index cbb1aedf5..3078ce05b 100644
--- a/src/crewai/knowledge/source/text_file_knowledge_source.py
+++ b/src/crewai/knowledge/source/text_file_knowledge_source.py
@@ -13,6 +13,7 @@ class TextFileKnowledgeSource(BaseFileKnowledgeSource):
         paths = [self.file_path] if isinstance(self.file_path, Path) else self.file_path
         content = {}
         for path in paths:
+            path = Path(path)
             with open(path, "r", encoding="utf-8") as f:
                 content[path] = f.read()
         return content