The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
[Bug fix] Fix issue with gmail loader (#1228)
Deshraj Yadav2985b667b013
diff --git a/docs/api-reference/app/chat.mdx b/docs/api-reference/app/chat.mdxindex b044777e0..ad0b20c9e 100644--- a/docs/api-reference/app/chat.mdx+++ b/docs/api-reference/app/chat.mdx@@ -129,3 +129,18 @@ app.chat("What is the net worth of Bill Gates?", session_id="user2")app.chat("What was my last question", session_id="user1")# 'Your last question was "What is the net worth of Elon Musk?"'```++### With custom context window++If you want to customize the context window that you want to use during chat (default context window is 3 document chunks), you can do using the following code snippet:++```python with custom chunks size+from embedchain import App+from embedchain.config import BaseLlmConfig++app = App()+app.add("https://www.forbes.com/profile/elon-musk")++query_config = BaseLlmConfig(number_documents=5)+app.chat("What is the net worth of Elon Musk?", config=query_config)+```diff --git a/docs/components/data-sources/custom.mdx b/docs/components/data-sources/custom.mdxindex 7d1515214..40a8c75e1 100644--- a/docs/components/data-sources/custom.mdx+++ b/docs/components/data-sources/custom.mdx@@ -7,11 +7,12 @@ When we say "custom", we mean that you can customize the loader and chunker to y```pythonfrom embedchain import Appimport your_loader-import your_chunker+from my_module import CustomLoader+from my_module import CustomChunkerapp = App()-loader = your_loader()-chunker = your_chunker()+loader = CustomLoader()+chunker = CustomChunker()app.add("source", data_type="custom", loader=loader, chunker=chunker)```diff --git a/embedchain/chunkers/base_chunker.py b/embedchain/chunkers/base_chunker.pyindex 6ce10b67e..b4d50f78d 100644--- a/embedchain/chunkers/base_chunker.py+++ b/embedchain/chunkers/base_chunker.py@@ -39,11 +39,14 @@ class BaseChunker(JSONSerializable):for data in data_records:content = data["content"]- meta_data = data["meta_data"]+ metadata = data["meta_data"]# add data type to meta data to allow query using data type- meta_data["data_type"] = self.data_type.value- meta_data["doc_id"] = doc_id- url = meta_data["url"]+ metadata["data_type"] = self.data_type.value+ metadata["doc_id"] = doc_id++ # TODO: Currently defaulting to the src as the url. This is done intentianally since some+ # of the data types like 'gmail' loader doesn't have the url in the meta data.+ url = metadata.get("url", src)chunks = self.get_chunks(content)for chunk in chunks:@@ -53,7 +56,7 @@ class BaseChunker(JSONSerializable):id_map[chunk_id] = Truechunk_ids.append(chunk_id)documents.append(chunk)- metadatas.append(meta_data)+ metadatas.append(metadata)return {"documents": documents,"ids": chunk_ids,diff --git a/pyproject.toml b/pyproject.tomlindex 452d0cec2..0b333d858 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -1,6 +1,6 @@[tool.poetry]name = "embedchain"-version = "0.1.71"+version = "0.1.72"description = "Simplest open source retrieval(RAG) framework"authors = ["Taranjeet Singh <[email protected]>",