update readme

.gitignore

@@ -1,3 +1,5 @@
+.vscode
 .venv
 dist
+
 **__pycache__/

README.md

@@ -30,12 +30,13 @@ Cria is a library for programatically running Large Language Models through Pyth
   - [Closing](#closing)
   - [Message History](#message-history)
   - [Multiple Models and Parallel Conversations](#multiple-models-and-parallel-conversations)
+  - [Running Standalone](#running-standalone)
 - [Contributing](#contributing)
 - [License](#license)
 
 ## Quickstart
 
-Running Cria is easy, after installation, you need just five lines of code.
+Running Cria is easy. After installation, you need just five lines of code — no configurations, no manual downloads, and no servers to worry about.
 
 ```python
 import cria
@@ -142,6 +143,30 @@ response = ai.chat(prompt, stream=False)
 print(response) # I apologize, but I don't have any information about "him" because the conversation just started...
 ```
 
+You can also create a custom message history, and pass in your own context.
+
+```python
+context = "Our AI system employed a hybrid approach combining reinforcement learning and generative adversarial networks (GANs) to optimize the decision-making..."
+messages = [
+    {"role": "system", "content": "You are a technical documentation writer"},
+    {"role": "user", "content": context},
+]
+
+prompt = "Write some documentation using the text I gave you."
+for chunk in ai.chat(messages=messages, prompt=prompt):
+    print(chunk, end="") # AI System Optimization: Hybrid Approach Combining Reinforcement Learning and...
+```
+
+In the example, instructions are given to the LLM and context is given as the user, before the user prompts. You can use any mixture of roles to specify the LLM to your liking.
+
+The available roles for messages are:
+
+- `user` - Pass prompts as the user.
+- `system` - Give instructions as the system.
+- `assistant` - Act as the AI assistant yourself, and give the LLM lines.
+
+The prompt parameter will always be appended to messages under the `user` role, to override this, you can choose to pass in nothing for `prompt`.
+
 ### Multiple Models and Parallel Conversations
 
 If you are running multiple models or parallel conversations, the `Model` class is also available. This is recommended for most usecases.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cria"
-version = "1.4.0"
+version = "1.4.1"
 authors = [{ name = "leftmove", email = "100anonyo@gmail.com" }]
 description = "Run AI locally with as little friction as possible"
 readme = "README.md"
@@ -17,7 +17,7 @@ Issues = "https://github.com/leftmove/cria/issues"
 
 [tool.poetry]
 name = "cria"
-version = "1.4.0"
+version = "1.4.1"
 description = "Run AI locally with as little friction as possible."
 authors = ["leftmove"]
 license = "MIT"

src/cria.py

@@ -6,11 +6,10 @@
 import subprocess
 import time
 
+from httpx import ConnectError, ReadError
 from ollama._client import Client as OllamaClient
 import ollama
 
-from httpx import ConnectError, ReadError
-
 DEFAULT_MODEL = "llama3:8b"
 DEFAULT_MESSAGE_HISTORY = [
     {"role": "system", "content": "You are a helpful AI assistant."}
@@ -76,19 +75,25 @@ def chat_stream(self, messages):
 
     def chat(
         self,
-        prompt: str,
+        prompt: Optional[str] = None,
         messages: Optional[list] = DEFAULT_MESSAGE_HISTORY,
         stream: Optional[bool] = True,
     ) -> str:
         model = self.model
         ai = ollama
 
-        messages = getattr(
-            self,
-            "messages",
-            messages,
-        )
-        messages.append({"role": "user", "content": prompt})
+        if not prompt and not messages:
+            raise ValueError("You must pass in a prompt.")
+
+        if messages == DEFAULT_MESSAGE_HISTORY:
+            messages = getattr(
+                self,
+                "messages",
+                messages,
+            )
+
+        if prompt:
+            messages.append({"role": "user", "content": prompt})
 
         if stream:
             return self.chat_stream(messages)
@@ -218,7 +223,7 @@ def output(self):
                 "You must pass in capture_ouput as True to capture output."
             )
 
-        return iter(lambda: ollama_subprocess.stdout.read(1), "")
+        return iter(c for c in iter(lambda: ollama_subprocess.stdout.read(1), b""))
 
     def close(self):
         llm = self.llm