[Docs Agent] Docs Agent release version 0.3.6

examples/gemini/python/docs-agent/README.md

@@ -7,9 +7,9 @@ Docs Agent provides a set of easy-to-use self-service tools designed to give you
 your team access to Google's [Gemini API][genai-doc-site] for learning, experimentation,
 and project deployment.
 
-## Overview
+## Docs Agent web app
 
-Docs Agent apps use a technique known as Retrieval Augmented Generation (RAG), which
+Docs Agent uses a technique known as **Retrieval Augmented Generation (RAG)**, which
 allows you to bring your own documents as knowledge sources to AI language models.
 This approach helps the AI language models to generate relevant and accurate responses
 that are grounded in the information that you provide and control.
@@ -18,13 +18,24 @@ that are grounded in the information that you provide and control.
 
 **Figure 1**. Docs Agent uses a vector database to retrieve context for augmenting prompts.
 
-Docs Agent apps are designed to be easily set up and configured in a Linux environment.
-If you want to set up and launch the Docs Agent chat app on your host machine, check out
-the [Set up Docs Agent][set-up-docs-agent] section below.
+The Docs Agent chatbot web app is designed to be easily set up and configured in a Linux
+environment. If you want to set up and launch the Docs Agent chat app on your host machine,
+check out the [Set up Docs Agent][set-up-docs-agent] section below.
 
-### Summary of features
+## Docs Agent tasks
 
-The following list summarizes the tasks and features supported by Docs Agent:
+Docs Agent's `agent runtask` command allows you to run pre-defined chains of prompts,
+which are referred to as **tasks**. These tasks simplify complex interactions by defining
+a series of steps that the Docs Agent will execute. The tasks are defined in `.yaml` files
+stored in the [`tasks`][tasks-dir] directory of your Docs Agent project. The tasks are
+designed to be reusable and can be used to automate common workflows, such as generating
+release notes, updating documentation, or analyzing complex information.
+
+To set up and run the `agent runtask` command, see [Set up Docs Agent CLI][cli-readme].
+
+## Summary of features
+
+The list below summarizes the tasks and features supported by Docs Agent:
 
 - **Process Markdown**: Split Markdown files into small plain text chunks. (See
   [Docs Agent chunking process][chunking-process].)
@@ -60,9 +71,9 @@ The following list summarizes the tasks and features supported by Docs Agent:
   [Set up the Docs Agent CLI][cli-readme] to make requests to the Gemini models
   from anywhere in a terminal.
 - **Support the Gemini 1.5 models**: Docs Agent works with the Gemini 1.5 models,
-  `gemini-1.5-pro-latest` and `text-embedding-004`. The new ["1.5"][new-15-mode] web app
-  mode uses all three Gemini models to their strength: AQA (`aqa`), Gemini 1.0 Pro
-  (`gemini-pro`), and Gemini 1.5 Pro (`gemini-1.5-pro-latest`).
+  `gemini-1.5-pro`, `gemini-1.5-flash`, and `text-embedding-004`. The new
+  [`full`][new-15-mode] web app mode uses all three Gemini models to their strength:
+  AQA (`aqa`), Gemini 1.0 Pro (`gemini-pro`), and Gemini 1.5 Pro (`gemini-1.5-pro`).
 - **Complete a task using the Docs Agent CLI**: The `agent runtask` command allows you
   to run pre-defined chains of prompts, which are referred to as tasks. These tasks
   simplify complex interactions by defining a series of steps that the Docs Agent will

examples/gemini/python/docs-agent/config.yaml

@@ -17,15 +17,15 @@
 configs:
   - product_name: "Fuchsia"
     models:
-      - language_model: "models/aqa"
+      - language_model: "models/gemini-1.5-flash-latest"
         embedding_model: "models/embedding-001"
         api_endpoint: "generativelanguage.googleapis.com"
         embedding_api_call_limit: 1400
         embedding_api_call_period: 60
     docs_agent_config: "normal"
     markdown_splitter: "token_splitter"
     log_level: "NORMAL"
-    db_type: "google_semantic_retriever"
+    db_type: "chroma"
     db_configs:
       - db_type: "chroma"
         vector_db_dir: "vector_stores/chroma"

examples/gemini/python/docs-agent/docs/cli-reference.md

@@ -273,8 +273,29 @@ For example:
 agent runtask --task DraftReleaseNotes
 ```
 
+### View the list of available Docs Agent tasks
+
 To see the list of all tasks available in your project, run
-`agent runtask` without any arguments.
+`agent runtask` without any arguments:
+
+```sh
+agent runtask
+```
+
+### Ask the model to run a task using custom input
+
+If a task script has a `<INPUT>` placeholder, you can provide
+a custom input string to the task:
+
+```sh
+agent runtask --task <TASK> --custom_input <INPUT_STRING>
+```
+
+For example:
+
+```sh
+agent runtask --task IndexPageGenerator --custom_input ~/my_example/docs/development/
+```
 
 ## Managing online corpora
 

examples/gemini/python/docs-agent/docs_agent/agents/docs_agent.py

@@ -359,7 +359,11 @@ def add_custom_instruction_to_context(self, condition, context):
 
     # Return true if the aqa model used in this Docs Agent setup
     def check_if_aqa_is_used(self):
-        if self.config.models.language_model == "models/aqa":
+        if (
+            self.config.models.language_model == "models/aqa"
+            or self.config.app_mode == "full"
+            or self.config.app_mode == "widget-pro"
+        ):
             return True
         else:
             return False
@@ -525,16 +529,21 @@ def ask_content_model_with_context_prompt(
         try:
             response = ""
             if model == "gemini-pro":
-                response = self.gemini_pro.generate_content(contents=new_prompt)
+                response = self.gemini_pro.generate_content(
+                    contents=new_prompt, log_level=self.config.log_level
+                )
             elif model == "gemini-1.5":
-                response = self.gemini_15.generate_content(contents=new_prompt)
+                response = self.gemini_15.generate_content(
+                    contents=new_prompt, log_level=self.config.log_level
+                )
             else:
-                response = self.gemini.generate_content(contents=new_prompt)
-        except:
+                response = self.gemini.generate_content(
+                    contents=new_prompt, log_level=self.config.log_level
+                )
+        except Exception as e:
+            print("Error in generate_content()")
+            print(e)
             return self.config.conditions.model_error_message, new_prompt
-        # for chunk in response:
-        #     if str(chunk.candidates[0].content) == "":
-        #         return self.config.conditions.model_error_message, new_prompt
         return response, new_prompt
 
     # Use this method for talking to a Gemini content model
@@ -549,9 +558,6 @@ def ask_content_model_to_use_file(self, prompt: str, file: str):
             response = self.gemini.generate_content(contents=new_prompt)
         except google.api_core.exceptions.InvalidArgument:
             return self.config.conditions.model_error_message
-        # for chunk in response:
-        #     if str(chunk.candidates[0].content) == "":
-        #         return self.config.conditions.model_error_message
         return response
 
     # Use this method for asking a Gemini content model for fact-checking.