### Pull Request for Issue #1246
**Description**,
This pull request addresses issue #1246, which proposes the addition of
a self-query retriever according to the LangChain Vectara integration.
The self-query retriever aims to empower users with the ability to
perform queries directly within the Vectara component(vector store).
**Changes Made**
I have added one more file under
`src\backend\langflow\components\retrievers` which contains a new
VectaraSelfQueryRetriverComponent class
**Files Added:** VectaraSelfQueryRetriever.py
**langchain documentation for this component:**
https://python.langchain.com/docs/integrations/retrievers/self_query/vectara_self_query
This pull request adds a Dockerfile for building and pushing the application image. The Dockerfile includes the necessary steps to set up the environment, install dependencies, and run the application.
fix(dropdownComponent): add condition to check if options object is
empty before rendering dropdown component
fix(chatInput): add condition to check if chatValue is an empty object
before displaying message
fix(chatMessage): remove useMemo hook and fix condition to check if chat
message is empty before displaying message
fix(formModal): add conditions to check if thought and files exist
before updating chat object
fix(genericModal): add condition to check if inputVariables exist before
displaying notice or success message
fix(chatInput): add condition to check if chatValue is an empty object before displaying message
fix(chatMessage): remove useMemo hook and fix condition to check if chat message is empty before displaying message
fix(formModal): add conditions to check if thought and files exist before updating chat object
fix(genericModal): add condition to check if inputVariables exist before displaying notice or success message
### Pull Request for Issue #1217
[feature
request](https://github.com/logspace-ai/langflow/labels/feature%20request)
[python](https://github.com/logspace-ai/langflow/labels/python)
**Description**
This pull request addresses issue #1217 , which concerns the ability to
add files directly to the Vectara vector store using the indexing API's
file upload feature.
**Changes Made**
I have implemented the ability to add files directly to the Vectara
vector store by providing URLs of documents online. The add_files()
method (as well as from_files()) has been added to facilitate this
functionality.
**Files Modified/Added**
Modified: vectara.py
This release of Langflow introduces a range of enhancements and notable
new features aimed at improving functionality, code quality, and user
experience. Key updates include the introduction of the Google Gemini
Component, a pivotal addition that expands the capabilities of Langflow
in language model applications.
Significant improvements were made in the custom component
functionality, notably in the areas of serialization and validation.
Basic support to LangChain Runnables added to the `process` endpoint.
On the front end, we've implemented changes to improve the overall user
interface and interactions. These include updates to the GenericNode
component, adjustments in the UI for better handling of nodes in the
flow, and the addition of new icon components for a more intuitive user
experience.
Backend refinements include updates to the Anthropic LLM and FAISS
component, along with several bug fixes and code optimizations. These
changes enhance the stability and efficiency of Langflow.
This pull request includes multiple code refactorings and updates to dependencies. It also removes unused imports, fixes code formatting, and updates the langflow version to 0.6.3a6.
