DOC-1241 Add history fields to chat completion processors (#225)

Author: asimms41

modules/components/pages/processors/ollama_chat.adoc

@@ -35,6 +35,7 @@ ollama_chat:
   max_tokens: 0 # No default (optional)
   temperature: 0 # No default (optional)
   save_prompt_metadata: false
+  history: "" # No default (optional)
   tools: [] # No default (required)
   runner:
     context_size: 0 # No default (optional)
@@ -67,6 +68,7 @@ ollama_chat:
   frequency_penalty: 0 # No default (optional)
   stop: [] # No default (optional)
   save_prompt_metadata: false
+  history: "" # No default (optional)
   max_tool_calls: 3
   tools: [] # No default (required)
   runner:
@@ -247,6 +249,26 @@ Set to `true` to save the prompt value to a metadata field (`@prompt`) on the co
 *Default*: `false`
 
 
+=== `history`
+
+Include historical messages in a chat request. You must use a Bloblang query to create an array of objects in the form of `[{"role": "", "content":""}]` where:
+
+- `role` is the sender of the original messages, either `system`, `user`, `assistant`, or `tool`.
+- `content` is the text of the original messages.
+
+*Type*: `string`
+
+*Default*: `""`
+
+```yml
+# Examples
+
+history: [{"role": "user", "content": "My favorite color is blue"}, {"role":"assistant", "content":"Nice"}]
+
+```
+If the `prompt` is set to `"What is my favorite color?"`, the specified `model` responds with `blue`.
+
+
 === `max_tool_calls`
 
 The maximum number of sequential calls you can make to external tools to retrieve additional information to answer a prompt.
@@ -449,6 +471,7 @@ output:
 ```
 --
 
+
 Use a series of processors to make calls to external tools::
 +
 --

modules/components/pages/processors/openai_chat_completion.adoc

@@ -31,6 +31,7 @@ openai_chat_completion:
   model: gpt-4o # No default (required)
   prompt: "" # No default (optional)
   system_prompt: "" # No default (optional)
+  history: "" # No default (optional)
   image: 'root = this.image.decode("base64") # decode base64 encoded image' # No default (optional)
   max_tokens: 0 # No default (optional)
   temperature: 0 # No default (optional)
@@ -56,6 +57,7 @@ openai_chat_completion:
   model: gpt-4o # No default (required)
   prompt: "" # No default (optional)
   system_prompt: "" # No default (optional)
+  history: "" # No default (optional)
   image: 'root = this.image.decode("base64") # decode base64 encoded image' # No default (optional)
   max_tokens: 0 # No default (optional)
   temperature: 0 # No default (optional)
@@ -156,6 +158,28 @@ The system prompt to submit along with the user prompt. This field supports xref
 
 *Type*: `string`
 
+=== `history`
+
+Include messages from a prior conversation. You must use a Bloblang query to create an array of objects in the form of `[{"role": "user", "content": "<text>"}, {"role":"assistant", "content":"<text>"}]` where:
+
+- `role` is the sender of the original messages, either `system`, `user`, or `assistant`.
+- `content` is the text of the original messages.
+
+For more information, see <<Examples, Examples>>.
+
+*Type*: `string`
+
+*Default*: `""`
+
+```yml
+# Examples
+
+history: [{"role": "user", "content": "My favorite color is blue"}, {"role":"assistant", "content":"Nice"}]
+
+```
+If the `prompt` is set to `"What is my favorite color?"`, the specified `model` responds with `blue`.
+
+
 === `image`
 
 An optional image to submit along with the prompt. The result of the Bloblang mapping must be a byte array.
@@ -660,6 +684,58 @@ output:
     codec: lines: lines
 ```
 
+--
+Generate chat history::
++
+--
+In this configuration, a pipeline executes a number of processors, including a cache, to generate and send chat history to a GPT-4o model.
+
+```yaml
+input: 
+  stdin:
+    scanner:
+      lines: {}
+pipeline:
+  processors:
+    - mapping: |
+        root.prompt = content().string()
+    - branch:
+        processors: 
+          - cache:
+              resource: mem
+              operator: get
+              key: history
+          - catch: 
+            - mapping: 'root = []'
+        result_map: 'root.history = this'
+    - branch:
+        processors:
+        - openai_chat_completion:
+            model: gpt-4o
+            api_key: "${OPENAI_API_KEY}"
+            prompt: "${!this.prompt}"
+            history: 'root = this.history'
+        result_map: 'root.response = content().string()'
+    - mutation: |
+        root.history = this.history.concat([
+          {"role": "user", "content": this.prompt},
+          {"role": "assistant", "content": this.response},
+         ])
+    - cache:
+        resource: mem
+        operator: set
+        key: history
+        value: '${!this.history}'
+    - mapping: |
+        root = this.response
+output:
+  stdout:
+    codec: lines
+ 
+cache_resources:
+  - label: mem 
+    memory: {}
+```
 --
 
 Make calls to external tools::