9 add aliases to splitembed (#13)

* Added ability to alias embeddings

README.md

@@ -6,20 +6,31 @@
 
 The **Oracle AI Microservices Sandbox** provides a streamlined environment where developers and data scientists can explore the potential of Generative Artificial Intelligence (GenAI) combined with Retrieval-Augmented Generation (RAG) capabilities. By integrating **Oracle Database 23ai** AI Vector Search, the Sandbox enables users to enhance existing Large Language Models (LLMs) through RAG.
 
+## Sandbox Features
+
+- [Configuring Embedding and Chat Models](configuration/model_config)
+- [Splitting and Embedding Documentation](tools/split_embed)
+- [Storing Embedded Documents into the Oracle Database](tools/split_embed)
+- [Modifying System Prompts (Prompt Engineering)](tools/prompt_eng)
+- [Experimenting with **LLM** Parameters](chatbot)
+- [Testing Framework on auto-generated or existing Q&A datasets](test_framework)
+
 ## Getting Started
 
 The **Oracle AI Microservices Sandbox** is available to install in your own environment, which may be a developer's desktop, on-premises data center environment, or a cloud provider. It can be run either on a bare-metal, within a container, or in a Kubernetes Cluster.
 
-For more information, including additional information on **Setup and Configuration** please visit the [documentation](https://oracle-samples.github.io/oaim-sandbox)
+For more information, including more details on **Setup and Configuration** please visit the [documentation](https://oracle-samples.github.io/oaim-sandbox).
 
 ### Prerequisites
 
 - Oracle Database 23ai incl. Oracle Database 23ai Free
 - Python 3.11 (for running Bare-Metal)
 - Container Runtime e.g. docker/podman (for running in a Container)
 - Access to an Embedding and Chat Model:
-  - API Keys for Third-Party Chat Model
-  - On-Premises Chat Model
+  - API Keys for Third-Party Models
+  - On-Premises Models<sub>\*</sub>
+
+<sub>\*Oracle recommends running On-Premises Models on hardware with GPUs. For more information, please review the [Infrastructure](infrastructure/) documentation.</sub>
 
 #### Bare-Metal Installation
 
@@ -48,6 +59,8 @@ To run the application on bare-metal; download the [source](https://github.com/o
 
 1. Navigate to `http://localhost:8501`.
 
+1. [Configure](configuration) the Sandbox.
+
 #### Container Installation
 
 To run the application in a container; download the [source](https://github.com/oracle-samples/oaim-sandbox) and from the top-level directory:
@@ -68,6 +81,8 @@ To run the application in a container; download the [source](https://github.com/
 
 1. Navigate to `http://localhost:8501`.
 
+1. [Configure](configuration) the Sandbox.
+
 ## Contributing
 
 This project welcomes contributions from the community. Before submitting a pull request, please [review our contribution guide](./CONTRIBUTING.md).

app/.dockerignore

@@ -5,8 +5,9 @@
 **/__init__.py
 **/tests
 **/etc
-**/.streamlit/config.toml
-**/tns_admin
+# **/.streamlit/config.toml
+# **/tns_admin
+**/.pytest_cache
 # No shell scripts included except the entrypoint
 **/*.sh
 !entrypoint.sh

app/requirements.txt

@@ -11,26 +11,20 @@
 ### pip3 install -r app/requirements.txt
 
 ## Top-Level brings in the required dependencies, if adding modules, try to find the minimum required
-beautifulsoup4==4.12.3
-griffe==0.48.0
-giskard[llm]==2.15.0
-langchain==0.2.16
-langchain_community==0.2.16
-langchain_huggingface==0.0.3
-langchain_ollama==0.1.3
-langchain_openai==0.1.23
-llama_index==0.11.5
+giskard[llm]==2.15.1
+IPython==8.27.0
+langchain_community==0.3.0
+langchain_huggingface==0.1.0
+langchain_ollama==0.2.0
+langchain_openai==0.2.0
+llama_index==0.11.10
 lxml==5.3.0
-oci>=2.131.0
-oracledb>=2.3.0
-plotly==5.24.0
-pytest>=8.3.2
-setuptools>=74.1.0
+oci>=2.0.0
+oracledb>=2.0.0
+plotly==5.24.1
 streamlit==1.38.0
-IPython==8.27.0
-pypdf==4.3.1
 
 ## For Licensing Purposes... this ensures no GPU modules
 -f https://download.pytorch.org/whl/cpu/torch
 torch==2.4.1+cpu ; sys_platform == "linux"
-torch==2.2.2 ; sys_platform == "darwin"
+torch==2.2.2 ; sys_platform == "darwin"

app/src/content/chatbot.py

@@ -91,7 +91,7 @@ def main():
             chat_history.clear()
         lm_model = st_common.lm_sidebar()
     else:
-        st.error("No chat models are configured and/or enabled.", icon="🚨",)
+        st.error("No chat models are configured and/or enabled.", icon="🚨")
         st.stop()
 
     # RAG

app/src/content/import_settings.py

@@ -33,10 +33,9 @@ def compare_dicts_recursive(current, uploaded):
             nested_diff = compare_dicts_recursive(current[key], uploaded[key])
             if nested_diff:
                 diff[key] = nested_diff
-        elif current.get(key) != uploaded.get(key):
-            if uploaded.get(key) != "":
-                # Report differences for non-dict values
-                diff[key] = {"current": current.get(key), "uploaded": uploaded.get(key)}
+        elif current.get(key) != uploaded.get(key) and uploaded.get(key) != "":
+            # Report differences for non-dict values
+            diff[key] = {"current": current.get(key), "uploaded": uploaded.get(key)}
 
     return diff
 
@@ -59,6 +58,7 @@ def compare_with_uploaded_json(current_state, uploaded_json):
 
 
 def update_session_state_recursive(session_state, updates):
+    """Apply settings to the Session State"""
     for key, value in updates.items():
         if value == "" or value is None:
             # Skip empty string values

app/src/content/model_config.py

@@ -38,7 +38,6 @@ def initialise_streamlit():
             "COSINE": [DistanceStrategy.COSINE],
             "EUCLIDEAN_DISTANCE": [DistanceStrategy.DOT_PRODUCT],
             "DOT_PRODUCT": [DistanceStrategy.EUCLIDEAN_DISTANCE],
-            "JACCARD": [DistanceStrategy.JACCARD],
             "MAX_INNER_PRODUCT": [DistanceStrategy.MAX_INNER_PRODUCT],
         }
         logger.info("Initialised Distance Metric Config")

app/src/content/oci_config.py

@@ -28,7 +28,7 @@ def initialise_streamlit():
     if "oci_configured" in state:
         return
 
-    logger.info("Initialising OCI Configuration")
+    logger.info("Initializing OCI Configuration")
     if "oci_config" not in state:
         state.oci_config = oci_utils.initialise()
     try:
@@ -108,7 +108,7 @@ def main():
                 st.success("OCI API Authentication Tested Successfully", icon="✅")
                 state.oci_config = test_config
                 st.success("OCI Configuration Saved", icon="✅")
-                state.oci_configred = True
+                state.oci_configured = True
             except oci_utils.OciException as ex:
                 logger.exception(ex, exc_info=False)
                 st.error(ex, icon="🚨")