From d6493b0e7fc1b05b4b218c689c0af7bbfd5db53a Mon Sep 17 00:00:00 2001
From: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Date: Wed, 21 Aug 2024 13:03:41 -0700
Subject: [PATCH] docs semantic caching qdrant

---
 docs/my-website/docs/proxy/caching.md        | 100 +++++++++++--------
 litellm/proxy/common_utils/callback_utils.py |  14 ++-
 litellm/proxy/proxy_server.py                |   8 +-
 3 files changed, 73 insertions(+), 49 deletions(-)

diff --git a/docs/my-website/docs/proxy/caching.md b/docs/my-website/docs/proxy/caching.md
index 71fae3e805..c2adca88a0 100644
--- a/docs/my-website/docs/proxy/caching.md
+++ b/docs/my-website/docs/proxy/caching.md
@@ -104,6 +104,66 @@ $ litellm --config /path/to/config.yaml
 ```
 </TabItem>
 
+
+<TabItem value="qdrant-semantic" label="Qdrant Semantic cache">
+
+Caching can be enabled by adding the `cache` key in the `config.yaml`
+
+#### Step 1: Add `cache` to the config.yaml
+```yaml
+model_list:
+  - model_name: fake-openai-endpoint
+    litellm_params:
+      model: openai/fake
+      api_key: fake-key
+      api_base: https://exampleopenaiendpoint-production.up.railway.app/
+  - model_name: openai-embedding
+    litellm_params:
+      model: openai/text-embedding-3-small
+      api_key: os.environ/OPENAI_API_KEY
+
+litellm_settings:
+  set_verbose: True
+  cache: True          # set cache responses to True, litellm defaults to using a redis cache
+  cache_params:
+    type: qdrant-semantic
+    qdrant_semantic_cache_embedding_model: openai-embedding # the model should be defined on the model_list
+    qdrant_collection_name: test_collection
+    qdrant_quantization_config: binary
+    similarity_threshold: 0.8   # similarity threshold for semantic cache
+```
+
+#### Step 2: Add Qdrant Credentials to your .env
+
+```shell
+QDRANT_API_KEY = "16rJUMBRx*************"
+QDRANT_API_BASE = "https://5392d382-45*********.cloud.qdrant.io"
+```
+
+#### Step 3: Run proxy with config
+```shell
+$ litellm --config /path/to/config.yaml
+```
+
+
+#### Step 4. Test it
+
+```shell
+curl -i http://localhost:4000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer sk-1234" \
+  -d '{
+    "model": "fake-openai-endpoint",
+    "messages": [
+      {"role": "user", "content": "Hello"}
+    ]
+  }'
+```
+
+**Expect to see `x-litellm-semantic-similarity` in the response headers when semantic caching is one**
+
+</TabItem>
+
 <TabItem value="s3" label="s3 cache">
 
 #### Step 1: Add `cache` to the config.yaml
@@ -185,46 +245,6 @@ $ litellm --config /path/to/config.yaml
 </TabItem>
 
 
-<TabItem value="qdrant-semantic" label="Qdrant Semantic cache">
-
-Caching can be enabled by adding the `cache` key in the `config.yaml`
-
-#### Step 1: Add `cache` to the config.yaml
-```yaml
-model_list:
-  - model_name: fake-openai-endpoint
-    litellm_params:
-      model: openai/fake
-      api_key: fake-key
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-  - model_name: openai-embedding
-    litellm_params:
-      model: openai/text-embedding-3-small
-      api_key: os.environ/OPENAI_API_KEY
-
-litellm_settings:
-  set_verbose: True
-  cache: True          # set cache responses to True, litellm defaults to using a redis cache
-  cache_params:
-    type: qdrant-semantic
-    qdrant_semantic_cache_embedding_model: openai-embedding # the model should be defined on the model_list
-    qdrant_collection_name: test_collection
-    qdrant_quantization_config: binary
-    similarity_threshold: 0.8   # similarity threshold for semantic cache
-```
-
-#### Step 2: Add Qdrant Credentials to your .env
-
-```shell
-QDRANT_API_KEY = "16rJUMBRx*************"
-QDRANT_API_BASE = "https://5392d382-45*********.cloud.qdrant.io"
-```
-
-#### Step 3: Run proxy with config
-```shell
-$ litellm --config /path/to/config.yaml
-```
-</TabItem>
 
 </Tabs>
 
diff --git a/litellm/proxy/common_utils/callback_utils.py b/litellm/proxy/common_utils/callback_utils.py
index 243ae18135..fa976690e6 100644
--- a/litellm/proxy/common_utils/callback_utils.py
+++ b/litellm/proxy/common_utils/callback_utils.py
@@ -285,14 +285,18 @@ def get_remaining_tokens_and_requests_from_request_data(data: Dict) -> Dict[str,
     return headers
 
 
-def get_applied_guardrails_header(request_data: Dict) -> Optional[Dict]:
+def get_logging_caching_headers(request_data: Dict) -> Optional[Dict]:
     _metadata = request_data.get("metadata", None) or {}
+    headers = {}
     if "applied_guardrails" in _metadata:
-        return {
-            "x-litellm-applied-guardrails": ",".join(_metadata["applied_guardrails"]),
-        }
+        headers["x-litellm-applied-guardrails"] = ",".join(
+            _metadata["applied_guardrails"]
+        )
 
-    return None
+    if "semantic-similarity" in _metadata:
+        headers["x-litellm-semantic-similarity"] = str(_metadata["semantic-similarity"])
+
+    return headers
 
 
 def add_guardrail_to_applied_guardrails_header(
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 12069d5e85..a9d0325d80 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -149,7 +149,7 @@ from litellm.proxy.common_utils.admin_ui_utils import (
     show_missing_vars_in_env,
 )
 from litellm.proxy.common_utils.callback_utils import (
-    get_applied_guardrails_header,
+    get_logging_caching_headers,
     get_remaining_tokens_and_requests_from_request_data,
     initialize_callbacks_on_proxy,
 )
@@ -543,9 +543,9 @@ def get_custom_headers(
         )
         headers.update(remaining_tokens_header)
 
-        applied_guardrails = get_applied_guardrails_header(request_data)
-        if applied_guardrails:
-            headers.update(applied_guardrails)
+        logging_caching_headers = get_logging_caching_headers(request_data)
+        if logging_caching_headers:
+            headers.update(logging_caching_headers)
 
     try:
         return {