MSCetin37
diff --git a/‎CodeGen/Dockerfile‎
Lines changed: 45 additions & 2 deletions b/‎CodeGen/Dockerfile‎
Lines changed: 45 additions & 2 deletions
diff --git a/‎CodeGen/README.md‎
Lines changed: 59 additions & 13 deletions b/‎CodeGen/README.md‎
Lines changed: 59 additions & 13 deletions
@@ -1,8 +1,51 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-ARG BASE_TAG=latest
-FROM opea/comps-base:$BASE_TAG
+# Stage 1: base setup used by other stages
+FROM python:3.11-slim AS base
+
+# get security updates
+RUN apt-get update && apt-get upgrade -y && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+ENV HOME=/home/user
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p $HOME && \
+    chown -R user $HOME
+
+WORKDIR $HOME
+
+
+# Stage 2: latest GenAIComps sources
+FROM base AS git
+
+RUN apt-get update && apt-get install -y --no-install-recommends git
+# RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git
+COPY GenAIComps GenAIComps
+
+
+# Stage 3: common layer shared by services using GenAIComps
+FROM base AS comps-base
+
+# copy just relevant parts
+COPY --from=git $HOME/GenAIComps/comps $HOME/GenAIComps/comps
+COPY --from=git $HOME/GenAIComps/*.* $HOME/GenAIComps/LICENSE $HOME/GenAIComps/
+
+WORKDIR $HOME/GenAIComps
+RUN pip install --no-cache-dir --upgrade pip setuptools && \
+    pip install --no-cache-dir -r $HOME/GenAIComps/requirements.txt
+WORKDIR $HOME
+
+ENV PYTHONPATH=$PYTHONPATH:$HOME/GenAIComps
+
+USER user
+
+
+# Stage 4: unique part
+FROM comps-base
+
+ENV LANG=C.UTF-8
 
 COPY ./codegen.py $HOME/codegen.py
 
 
@@ -1,6 +1,6 @@
 # Code Generation Application
 
-Code Generation (CodeGen) Large Language Models (LLMs) are specialized AI models designed for the task of generating computer code. Such models undergo training with datasets that encompass repositories, specialized documentation, programming code, relevant web content, and other related data. They possess a deep understanding of various programming languages, coding patterns, and software development concepts. CodeGen LLMs are engineered to assist developers and programmers. When these LLMs are seamlessly integrated into the developer's Integrated Development Environment (IDE), they possess a comprehensive understanding of the coding context, which includes elements such as comments, function names, and variable names. This contextual awareness empowers them to provide more refined and contextually relevant coding suggestions.
+Code Generation (CodeGen) Large Language Models (LLMs) are specialized AI models designed for the task of generating computer code. Such models undergo training with datasets that encompass repositories, specialized documentation, programming code, relevant web content, and other related data. They possess a deep understanding of various programming languages, coding patterns, and software development concepts. CodeGen LLMs are engineered to assist developers and programmers. When these LLMs are seamlessly integrated into the developer's Integrated Development Environment (IDE), they possess a comprehensive understanding of the coding context, which includes elements such as comments, function names, and variable names. This contextual awareness empowers them to provide more refined and contextually relevant coding suggestions. Additionally Retrieval-Augmented Generation (RAG) and Agents are parts of the CodeGen example which provide an additional layer of intelligence and adaptability, ensuring that the generated code is not only relevant but also accurate, efficient, and tailored to the specific needs of the developers and programmers.
 
 The capabilities of CodeGen LLMs include:
 
@@ -20,6 +20,7 @@ The workflow falls into the following architecture:
 
 The CodeGen example is implemented using the component-level microservices defined in [GenAIComps](https://github.com/opea-project/GenAIComps). The flow chart below shows the information flow between different microservices for this example.
 
+
 ```mermaid
 ---
 config:
@@ -28,7 +29,7 @@ config:
     rankSpacing: 100
     curve: linear
   themeVariables:
-    fontSize: 50px
+    fontSize: 25px
 ---
 flowchart LR
     %% Colors %%
@@ -37,34 +38,56 @@ flowchart LR
     classDef orchid fill:#C26DBC,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
     classDef invisible fill:transparent,stroke:transparent;
     style CodeGen-MegaService stroke:#000000
-
     %% Subgraphs %%
-    subgraph CodeGen-MegaService["CodeGen MegaService "]
+    subgraph CodeGen-MegaService["CodeGen-MegaService"]
         direction LR
-        LLM([LLM MicroService]):::blue
+        EM([Embedding<br>MicroService]):::blue
+        RET([Retrieval<br>MicroService]):::blue
+        RER([Agents]):::blue
+        LLM([LLM<br>MicroService]):::blue
     end
-    subgraph UserInterface[" User Interface "]
+    subgraph User Interface
         direction LR
-        a([User Input Query]):::orchid
-        UI([UI server<br>]):::orchid
+        a([Submit Query Tab]):::orchid
+        UI([UI server]):::orchid
+        Ingest([Manage Resources]):::orchid
     end
 
+    CLIP_EM{{Embedding<br>service}}
+    VDB{{Vector DB}}
+    V_RET{{Retriever<br>service}}
+    Ingest{{Ingest data}}
+    DP([Data Preparation]):::blue
+    LLM_gen{{TGI Service}}
+    GW([CodeGen GateWay]):::orange
 
-    LLM_gen{{LLM Service <br>}}
-    GW([CodeGen GateWay<br>]):::orange
-
+    %% Data Preparation flow
+    %% Ingest data flow
+    direction LR
+    Ingest[Ingest data] --> UI
+    UI --> DP
+    DP <-.-> CLIP_EM
 
     %% Questions interaction
     direction LR
     a[User Input Query] --> UI
     UI --> GW
     GW <==> CodeGen-MegaService
+    EM ==> RET
+    RET ==> RER
+    RER ==> LLM
 
 
     %% Embedding service flow
     direction LR
+    EM <-.-> CLIP_EM
+    RET <-.-> V_RET
     LLM <-.-> LLM_gen
 
+    direction TB
+    %% Vector DB interaction
+    V_RET <-.->VDB
+    DP <-.->VDB
 ```
 
 ## Deploy CodeGen Service
@@ -138,11 +161,25 @@ Refer to the [Gaudi Guide](./docker_compose/intel/hpu/gaudi/README.md) to build
 
 Find the corresponding [compose.yaml](./docker_compose/intel/cpu/xeon/compose.yaml).
 
+Start CodeGen based on TGI service:
+
 ```bash
-cd GenAIExamples/CodeGen/docker_compose/intel/cpu/xeon
-docker compose up -d
+cd GenAIExamples/CodeGen/docker_compose
+source set_env.sh
+cd intel/cpu/xeon
+docker compose --profile codegen-xeon-tgi up -d
+```
+
+Start CodeGen based on vLLM service:
+
+```bash
+cd GenAIExamples/CodeGen/docker_compose
+source set_env.sh
+cd intel/cpu/xeon
+docker compose --profile codegen-xeon-vllm up -d
 ```
 
+
 Refer to the [Xeon Guide](./docker_compose/intel/cpu/xeon/README.md) for more instructions on building docker images from source.
 
 ### Deploy CodeGen on Kubernetes using Helm Chart
@@ -161,6 +198,15 @@ Two ways of consuming CodeGen Service:
        -d '{"messages": "Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception."}'
    ```
 
+   If the user wants a CodeGen service with RAG and Agents based on dedicated documentation.
+
+   ```bash
+   curl http://localhost:7778/v1/codegen \
+      -H "Content-Type: application/json" \
+      -d '{"agents_flag": "True", "index_name": "my_API_document", "messages": "Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception."}'
+
+   ```
+
 2. Access via frontend
 
    To access the frontend, open the following URL in your browser: http://{host_ip}:5173.