Fix langchain llm and update changelog (#2508)

Author: Dev-Khant

Makefile

@@ -13,7 +13,7 @@ install:
 install_all:
 	poetry install
 	poetry run pip install groq together boto3 litellm ollama chromadb weaviate weaviate-client sentence_transformers vertexai \
-	                        google-generativeai elasticsearch opensearch-py vecs pinecone pinecone-text faiss-cpu
+	                        google-generativeai elasticsearch opensearch-py vecs pinecone pinecone-text faiss-cpu langchain-community
 
 # Format code with ruff
 format:

docs/changelog/overview.mdx

@@ -6,6 +6,25 @@ mode: "wide"
 <Tabs>
 <Tab title="Python">
 
+<Update label="2025-04-07" description="v0.1.82">
+
+**New Features:**
+- **LLM Integrations:** Added support for Langchain LLMs, Google as new LLM and embedder
+- **Development:** Added development docker compose
+
+**Improvements:**
+- **Output Format:** Set output_format='v1.1' and updated documentation
+
+**Documentation:**
+- **Integrations:** Added LMStudio and Together.ai documentation
+- **API Reference:** Updated output_format documentation
+- **Integrations:** Added PipeCat integration documentation
+- **Integrations:** Added Flowise integration documentation for Mem0 memory setup
+
+**Bug Fixes:**
+- **Tests:** Fixed failing unit tests
+</Update>
+
 <Update label="2025-04-02" description="v0.1.79">
 
 **New Features:**
@@ -56,6 +75,17 @@ mode: "wide"
 
 <Tab title="TypeScript">
 
+<Update label="2025-04-01" description="v2.1.14">
+**New Features:**
+- **Mastra Example:** Added Mastra example
+- **Integrations:** Added Flowise integration documentation for Mem0 memory setup
+
+**Improvements:**
+- **Demo:** Updated Demo Mem0AI
+- **Client:** Enhanced Ping method in Mem0 Client
+- **AI SDK:** Updated AI SDK implementation
+</Update>
+
 <Update label="2025-03-29" description="v2.1.13">
 **Improvements:**
 - **Introuced `ping` method to check if API key is valid and populate org/project id**

mem0/llms/langchain.py

@@ -12,7 +12,7 @@
 
 # Provider-specific package mapping
 PROVIDER_PACKAGES = {
-    # "Anthropic": "langchain_anthropic", # Special handling for Anthropic with Pydantic v2
+    "Anthropic": "langchain_anthropic",
     "MistralAI": "langchain_mistralai",
     "Fireworks": "langchain_fireworks",
     "AzureOpenAI": "langchain_openai",
@@ -135,18 +135,25 @@ def __init__(self, config: Optional[BaseLlmConfig] = None):
         try:
             # Check if this provider needs a specialized package
             if provider in PROVIDER_PACKAGES:
-                package_name = PROVIDER_PACKAGES[provider]
-                try:
-                    # Import the model class directly from the package
-                    module_path = f"{package_name}"
-                    model_class = __import__(module_path, fromlist=[model_name])
-                    model_class = getattr(model_class, model_name)
-                except ImportError:
-                    raise ImportError(
-                        f"Package {package_name} not found. " f"Please install it with `pip install {package_name}`"
-                    )
-                except AttributeError:
-                    raise ImportError(f"Model {model_name} not found in {package_name}")
+                if provider == "Anthropic": # Special handling for Anthropic with Pydantic v2
+                    try:
+                        from langchain_anthropic import ChatAnthropic
+                        model_class = ChatAnthropic
+                    except ImportError:
+                        raise ImportError("langchain_anthropic not found. Please install it with `pip install langchain-anthropic`")
+                else:
+                    package_name = PROVIDER_PACKAGES[provider]
+                    try:
+                            # Import the model class directly from the package
+                        module_path = f"{package_name}"
+                        model_class = __import__(module_path, fromlist=[model_name])
+                        model_class = getattr(model_class, model_name)
+                    except ImportError:
+                        raise ImportError(
+                            f"Package {package_name} not found. " f"Please install it with `pip install {package_name}`"
+                        )
+                    except AttributeError:
+                        raise ImportError(f"Model {model_name} not found in {package_name}")
             else:
                 # Use the default langchain_community module
                 if not hasattr(chat_models, model_name):
@@ -158,8 +165,7 @@ def __init__(self, config: Optional[BaseLlmConfig] = None):
             self.langchain_model = model_class(
                 model=self.config.model,
                 temperature=self.config.temperature,
-                max_tokens=self.config.max_tokens,
-                api_key=self.config.api_key,
+                max_tokens=self.config.max_tokens
             )
         except (ImportError, AttributeError, ValueError) as e:
             raise ImportError(f"Error setting up langchain model for provider {provider}: {str(e)}")

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "mem0ai"
-version = "0.1.82"
+version = "0.1.83"
 description = "Long-term memory for AI Agents"
 authors = ["Mem0 <[email protected]>"]
 exclude = [