From fc5230dffadb5949e25c47ec85de0c8ff8d1bf70 Mon Sep 17 00:00:00 2001
From: Bruce MacDonald <brucewmacdonald@gmail.com>
Date: Mon, 14 Aug 2023 15:23:24 -0300
Subject: [PATCH 1/3] Add context to api docs

---
 docs/api.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/docs/api.md b/docs/api.md
index 9fec79a2..f361823b 100644
--- a/docs/api.md
+++ b/docs/api.md
@@ -38,6 +38,7 @@ Advanced parameters:
 - `options`: additional model parameters listed in the documentation for the [Modelfile](./modelfile.md#valid-parameters-and-values) such as `temperature`
 - `system`: system prompt to (overrides what is defined in the `Modelfile`)
 - `template`: the full prompt or prompt template (overrides what is defined in the `Modelfile`)
+- `context`: the context parameter returned from a previous request to `/generate`, this can be used to keep a short conversational memory
 
 ### Request
 
@@ -71,6 +72,7 @@ The final response in the stream also includes additional data about the generat
 - `prompt_eval_duration`: time spent in nanoseconds evaluating the prompt
 - `eval_count`: number of tokens the response
 - `eval_duration`: time in nanoseconds spent generating the response
+- `context`: an encoding of the conversation used in this response, this can be sent in the next request to keep a conversational memory
 
 To calculate how fast the response is generated in tokens per second (token/s), divide `eval_count` / `eval_duration`.
 
@@ -78,6 +80,7 @@ To calculate how fast the response is generated in tokens per second (token/s),
 {
   "model": "llama2:7b",
   "created_at": "2023-08-04T19:22:45.499127Z",
+  "context": [1, 2, 3],
   "done": true,
   "total_duration": 5589157167,
   "load_duration": 3013701500,

From 648f0974c6ad7cfff4eafade5891b1aefb3a1926 Mon Sep 17 00:00:00 2001
From: Bruce MacDonald <brucewmacdonald@gmail.com>
Date: Mon, 14 Aug 2023 15:27:13 -0300
Subject: [PATCH 2/3] python example

---
 docs/python/examples/client.py | 40 ++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)
 create mode 100644 docs/python/examples/client.py

diff --git a/docs/python/examples/client.py b/docs/python/examples/client.py
new file mode 100644
index 00000000..4d3faeb4
--- /dev/null
+++ b/docs/python/examples/client.py
@@ -0,0 +1,40 @@
+import json
+import requests
+
+# NOTE: ollama must be running for this to work, start the ollama app or run `ollama serve`
+model = 'llama2' # TODO: update this for whatever model you wish to use
+context = [] # the context stores a conversation history, you can use this to make the model more context aware
+
+def generate(prompt):
+    global context
+    r = requests.post('http://localhost:11434/api/generate',
+                      json={
+                          'model': model,
+                          'prompt': prompt,
+                          'context': context,
+                      },
+                      stream=True)
+    r.raise_for_status()
+
+    for line in r.iter_lines():
+        body = json.loads(line)
+        response_part = body.get('response', '')
+        # the response streams one token at a time, print that as we recieve it
+        print(response_part, end='', flush=True)
+
+        if 'error' in body:
+            raise Exception(body['error'])
+
+        if body.get('done', False):
+            context = body['context']
+            return
+
+def main():
+    while True:
+        user_input = input("Enter a prompt: ")
+        print()
+        generate(user_input)
+        print()
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file

From af98a1773f2d8c511090b07e0135971d97e851b7 Mon Sep 17 00:00:00 2001
From: Bruce MacDonald <brucewmacdonald@gmail.com>
Date: Mon, 14 Aug 2023 16:38:44 -0300
Subject: [PATCH 3/3] update python example

---
 {docs/python/examples => examples/python}/client.py | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)
 rename {docs/python/examples => examples/python}/client.py (79%)

diff --git a/docs/python/examples/client.py b/examples/python/client.py
similarity index 79%
rename from docs/python/examples/client.py
rename to examples/python/client.py
index 4d3faeb4..599ebec7 100644
--- a/docs/python/examples/client.py
+++ b/examples/python/client.py
@@ -3,10 +3,8 @@ import requests
 
 # NOTE: ollama must be running for this to work, start the ollama app or run `ollama serve`
 model = 'llama2' # TODO: update this for whatever model you wish to use
-context = [] # the context stores a conversation history, you can use this to make the model more context aware
 
-def generate(prompt):
-    global context
+def generate(prompt, context):
     r = requests.post('http://localhost:11434/api/generate',
                       json={
                           'model': model,
@@ -26,14 +24,14 @@ def generate(prompt):
             raise Exception(body['error'])
 
         if body.get('done', False):
-            context = body['context']
-            return
+            return body['context']
 
 def main():
+    context = [] # the context stores a conversation history, you can use this to make the model more context aware
     while True:
         user_input = input("Enter a prompt: ")
         print()
-        generate(user_input)
+        context = generate(user_input, context)
         print()
 
 if __name__ == "__main__":